Agent 进展

Occupants are a primary source of uncertainty in building energy consumption and management, yet existing occupant behavior models cannot capture adaptive and reasoning responses considering the occupant's personal history, current context, and the type of energy signal being delivered. This study presents BuildOcc, an open-source Python platform that grounds large language model agents in the American Time Use Survey (ATUS), a nationally representative diary dataset covering 16,684 respondents. Through BuildOcc, each simulated occupant agent can be instantiated with a demographic persona drawn from ATUS population statistics, a memory stream that accumulates and reflects on timestep-level observations, and an activity scheduler that samples empirically from ATUS time-at-activity distributions. The platform exposes a three-layer interface - Python library, REST API, and Model Context Protocol server - so that any building energy tool (EnergyPlus, Home Assistant) can integrate behavioral intelligence without bespoke coupling code. A plugin registry lets the community add new occupant strata, custom schedulers, and alternative memory backends as separate installable packages. Two validation tiers show that ATUS-grounded sampling reproduces empirically calibrated activity distributions and that demographic priors propagate into persona-consistent agent reasoning across timesteps, establishing internal consistency across strata. BuildOcc provides the building energy community with a reusable, openly available implementation of the occupant behavioral layer. BuildOcc is openly released at https://doi.org/10.5281/zenodo.21192895 under the Apache License 2.0 and installable via pip install buildocc.

Personalized language agents use persistent memory to adapt to users over time, but the same mechanism creates an attack surface. When new information conflicts with stored preferences, an agent must distinguish genuine preference drift from temporary context shifts, ambiguity, or adversarial memory poisoning. We formulate this problem as a continuous-time partially observable decision process over a latent user state and show why rules based only on recency and provenance are insufficient. CAPTURE addresses this ambiguity with a neural differential-equation belief tracker, a multi-timescale memory ledger, uncertainty-triggered clarification, and counterfactual auditing of cited memories. On 480 held-out episodes from 96 users, CAPTURE achieves a 71.5% win rate, compared with 69.3% for an identically supervised baseline and 66.1% for the strongest heuristic baseline. It limits fixed-policy poisoning success to 11.5% while accepting 83.5% of genuine preference updates. Under an adaptive attacker with access to the released weights, attack success rises to 24.7%, exposing a real adaptation-security tradeoff. We further evaluate the frozen system zero-shot on an independently constructed benchmark and replay longitudinal interaction histories from 40 users collected over two to three weeks. These results suggest that modeling preference authenticity explicitly can improve both personalization and robustness in memory-augmented LLM agents.

Human interventions at fault points can alter the diagnostic accuracy of multi-agent medical systems. We defined fault points as moments in AI agent conversations, in which an agent's reasoning became most vulnerable to external influence. Using the MedQA dataset, this study analyzed simulated doctor-patient conversations to measure how interventions shifted reasoning and accuracy. Correct intervention methods showed an improvement in baseline diagnostic accuracy of up to 40%, while incorrect or bias-related interventions degraded performance by up to 6% and increased diagnostic drift and uncertainty. Beyond performance changes, our analysis revealed behavioral similarities between cognitive biases in simulated agent environments and real-world clinical practice. Examples included premature closure and susceptibility to misleading cues. Overall, these findings demonstrate that identifying and guiding fault points with human interventions may provide a mechanism for improving diagnostic robustness in multi-agent medical systems.

Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification. We model orchestrator-worker interaction as a bilevel coordination game: under bounded coupling, the workers' local-update game is an approximate potential game whose equilibrium slack is controlled by decomposition quality. We then analyse reflection as stochastic movement over semantic memory states. For free-form reflection, we derive a finite-time upper bound, prove worst-case tightness, and give a positive lower bound under a falsifiable persistent-harm condition. We further prove an information-theoretic impossibility result: no gate that observes only the generated transcript can improve uniformly over text-indistinguishable environments, whereas an environment-grounded gate can. Motivated by this separation, we introduce Stochastic Reflective Memory Ascent (SRMA), which accepts a candidate memory only after a grounded evaluation risk strictly decreases. Under calibration and non-degenerate corrective mass, SRMA converges exactly, geometrically or polynomially; matching constructions show that both rate regimes are order-tight. We also provide confidence gating for stochastic evaluation and re-anchoring guarantees for piecewise-stationary environments. Experiments instantiate these objects with environment-grounded metrics and test the predicted coordination and drift laws. On 500 SWE-bench instances, the complete Kimi-based system resolves 72.2% versus a 70.8% public mini-SWE-agent reference. Code: https://github.com/YihangChen9/Bilevel-Coordinated-Reflection

Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user behavior, and upstream models shift, the choices governing retrieval, ranking, and serving must be revisited. Traditionally, human engineers test such changes through online experiments--a slow, reactive process limited by engineering effort, leaving parts of the system unrevised as conditions change. Although large language models have been applied to ranking, user modeling, and offline model development, few systems place an agent in a continual closed loop that acts on a live recommender and learns from the measured effects of its decisions. We present CORAL (Constraint-Optimized Recommender via an Agentic Loop), an LLM-native harness that closes this loop: each cycle, the agent observes operating signals, reasons over a memory of past decisions and outcomes, and invokes tools--including a numerical optimizer that keeps changes within a fixed operating budget--to reconfigure the recommender, with measured outcomes informing the next cycle. We formulate this as a partially observed, non-stationary, constrained optimization problem in which the policy improves in context, without parameter updates, from its prior actions. Across two large-scale social platforms, evaluated with A/B experiments, the same harness improves engagement at no additional serving cost on one and reduces serving cost without degrading engagement on the other, spanning the engagement-efficiency frontier. Performance improves as the loop iterates, suggesting that a single agentic loop can automate continual optimization work traditionally performed by human algorithm engineers under explicit guardrails.

The rapid proliferation of large language models (LLMs) and the growing diversity of their applications presents a unique optimization opportunity: selecting the right model for the task, while optimizing for speed, cost, and quality at a per-task level. However, inference endpoints can vary widely in quality, price, latency, context support, tool use, domain expertise, and reasoning behavior. This heterogeneity makes manual heuristics difficult to maintain and unlikely to achieve consistently favorable speed--cost--quality trade-offs on their own. We introduce \router{}, a lightweight GLiClass-based router that assigns a suitability score to each inference-time model label without autoregressive generation. The released 0.6B-parameter checkpoint combines a Qwen3 decoder with a shallow bidirectional scorer. Its decoder-KV execution path preserves a text-only key--value cache across a session, encodes only new dialogue turns, and evaluates transient candidate-label tokens without adding them to the persistent cache. The same checkpoint also predicts task type, difficulty, reasoning mode, and expected output length, and supports custom zero-shot labels. For task generation, we construct a task ontology with 23 families, 115 task types, 345 routable subtypes, 1,173 synthetic examples, and an orthogonal axis of 30 domains. Using this structure, we generate 150,000 verifier-scored tasks and 15,000 open-ended tasks. We then train the Qwen3 decoder on these tasks, while explicitly separating learned request prediction from per-task policies for attributes such as eligibility, cost, cache reuse, safety, and sovereignty. Across six LiveBench subsets, the router outperforms the mean candidate; on the selected 1,000-task subset, it achieves an aggregate top-1 score of 0.707 versus 0.696 for the strongest fixed model, with benchmark-dependent gains.

Wherever a coding agent works under engineer supervision, or a clinical model assists a radiologist, the deployment question is whether to keep the human-AI workflow or replace it with the human alone or the agent alone. The human-AI workflow is worth keeping only if it beats both of those alternatives. Yet once it is deployed, neither alternative outcome is observed: recovering one means replaying the task under that alternative, and every replay costs expert time or compute. Under a fixed replay budget, the design question is therefore which tasks should be more likely to receive a human-only replay, and which an agent-only replay. Existing methods do not directly target this decision. Agent benchmarks do not choose which missing baseline to measure, variance-based sampling ignores which of the two comparisons is closer to failing, and Bayesian information methods focus on learning model parameters instead of making the deployment decision. We propose TEAM-Design, a rule that gives every task two replay probabilities, one per baseline. It raises a probability where the missing baseline outcome is hard to predict from what is already known about the task and where that comparison is harder to establish, and lowers it where replay is expensive. We prove that the rule solves this budgeted design problem, and that drawing the replays at random from recorded probabilities still controls the chance of wrongly declaring that the workflow beats both. We reanalyze 6 clinical settings, where no human-AI workflow beats both alternatives, and a coding benchmark, where one does, then evaluate TEAM-Design on synthetic designs and on a semi-synthetic design built from a real chest X-ray reader study. TEAM-Design works best when one of the two comparisons is clearly harder to settle than the other, and can do worse than variance-based allocation when the two are similarly difficult.

Large language model (LLM)-based multi-agent systems (MAS) predominantly rely on centralized orchestration and lack formal verification mechanisms for agent reliability, participation, and system-level behavioral alignment. These shortcomings leave open environments severely vulnerable to uncooperative or malicious agents. This work proposes DART, a Directed Acyclic Graph (DAG)-based reputation and incentive regulation framework for trustworthy multi-agent collaboration, combining centralized operational orchestration with blockchain-enabled decentralized governance and accountability. DART unifies DAG workflow orchestration, capability and reputation-aware task allocation, dynamic behavior updates, multi-factor incentives, and smart contract accountability paired with IPFS storage. Under this paradigm, agent selection dynamically balances task alignment, historical reputation, and workload, while post-execution behavioral evidence continuously calibrates agent trust and the probability of future participation. Evaluated across four axes, DART achieves 93.6% Pass@1 on GSM8K and builds a full-stack application in 142 s using two agents, outperforming centralized baselines. Across five independent 150-round longitudinal trials, Full DART achieves a mean task success rate of 93.33 +/- 2.26%, output quality of 0.9357 +/- 0.0117, retry rate of 0.2307 +/- 0.0816, and allocation delay of 1.1153 +/- 0.0408 s, consistently outperforming its ablated configurations DART isolates persistent and intermittent malicious agents, obtaining a 99.3% output containment rate and restoring system success to 99.8%. These results demonstrate the potential of coupling reputation, incentives, DAG-based coordination, and verifiable blockchain-enabled governance to support adaptive and accountable multi-agent collaboration.

Future 6G networks will rely on Large Language Model (LLM) agents to manage the Radio Access Network (RAN). However, current architectures assume inter-agent messages convey objective facts. A message is instead a trace of the sender's reasoning: it carries a subjective conclusion, so a syntactically valid report can propagate an AI hallucination and trigger a cascading outage invisible to protocol validation. Reading such a trace requires a Theory of Mind (ToM)---before acting, the receiver must model what the peer believes, and what a peer in that position should have believed. Modeling these interactions as cognitive channels on a cellular sheaf, we obtain a unified framework for resilient multi-agent systems, from which five design principles emerge: (i) a message is evidence of the sender's hidden reasoning; (ii) trust is a continuous cognitive Signal-to-Noise Ratio (SNR)---asserted precision over deviation from the modeled peer belief; (iii) network-wide consistency and resistance to hallucination contagion are computable via the sheaf's Laplacian; (iv) peer-modeling must halt at exactly two levels to conserve compute and survive mutual information decay; and (v) credible capacity is bounded by operational goal alignment, not link bandwidth. A signaling-storm study on locally deployed 1B-parameter telecom language models validates it: cognitive SNR isolates a hallucinating peer that three of its four neighbors agree with, where a divergence gate ranks every wrong peer above the right one; only depth two ToM recovers the correct action; and the spectral gap decides whether a topology reaches consistency inside the near-real-time budget.

Large language model (LLM)-based multi-agent systems (MAS) have shown strong potential for solving complex tasks, yet their development forces a tradeoff: code frameworks are expressive but engineering-intensive, while no-code builders simplify authoring but constrain agent interactions to author-defined workflows. We present ChatDev 2.0: DevAll (hereafter DevAll), a no-code platform for building, executing, and inspecting heterogeneous MAS that delivers both high expressiveness and ease of use. In terms of expressiveness, DevAll pairs a declarative executable graph abstraction with a cycle-aware execution engine, so that heterogeneous agents and dynamic and cyclic interactions can be represented and executed within a single framework. For ease of use, an integrated visual interface lets users author, run, monitor, and inspect MAS, including human-in-the-loop steps, entirely without writing code. Experiments demonstrate that DevAll reproduces state-of-the-art MAS across three representative tasks at competitive performance and without task-specific orchestration code, highlighting its effectiveness as a general-purpose platform for LLM-based MAS. DevAll is available at https://github.com/OpenBMB/ChatDev.

Safety properties assessed separately for Model Context Protocol (MCP) tool use and Agent2Agent (A2A) delegation need not describe behavior when one agent uses both. We measure one such behavior in a single controlled MCP-to-A2A configuration: a testbed drives a real-model host across a local MCP and a local A2A leg into an ordered event trace scored by exact deterministic rules (no LLM judge), one restricted decision per trial. In a pre-specified, frozen three-arm design, each of 10 record scenarios appears with a CONFIDENTIAL header, with no header, and with PUBLIC - OK TO SHARE; the six substantive record values are byte-identical across arms, and the outcome is verbatim occurrence of any of them in the outbound message. Four models x 3 arms x 4 repeats give 480 trials; the scenario is the unit of generalization, and we report the 10 scenario-level values (mean, median, sign counts), with no p-values or intervals. The confidential-minus-unlabeled contrast is inconclusive and floor-limited in every model (both arms at or near zero), so it does not show that confidential labels lack a protective effect. Adding PUBLIC - OK TO SHARE is descriptively associated with higher verbatim egress relative to the unlabeled baseline, with strong model dependence: strong and consistent for Claude Sonnet 5 (public-minus-unlabeled mean +0.800, all 10 scenarios; mostly an association with whether Claude relays at all), moderate but floor-limited for one GPT-5.6 tier, small (median 0) for another, and a complete floor for the third. This is an association in one configuration, not a causal or general effect. Code, byte-pinned traces, and the offline analysis pipeline are released as a public artifact.

Persistent memory supports personalized agents, but a stale stored fact can override current authoritative evidence without warning. We study when this harm begins as model capability changes. We evaluate a frozen, closed-set, action-scored benchmark with 2 suites that represent 2 different meanings of "no memory" (a Benefit suite, unsolvable without the stored fact, and a Safety suite, in which an authoritative tool always holds the correct value), on a same-family model-size series (Qwen3 0.6/1.7/4/8B). The Memory Trust Gap reflects over-trust rather than confusion. In the Benefit suite, models answer with the stale value 0.92-1.00 of the time at every scale. In the Safety suite, harm below the no-memory baseline under the trap conditions ($Δ_{\mathrm{mem}}$) is capability-gated, with the larger models collapsing most once a stale note is made to look current. In a $2\times2\times2\times2$ factorial, which feature triggers over-trust depends on both the feature and model scale. Removing a label amplifies over-trust at every size, and a recency feature (stale dated newer) fools the larger models harder. Source authority is weak and scale-flat, and position changes from positive to negative across the Qwen3 model-size series. We confirm these scale interactions with direct cross-size contrast tests rather than overlapping per-model intervals. Mitigation is likewise capability-dependent: exposing metadata improves accuracy for the capable models, but only pre-resolving the conflict restores accuracy for the 2 smaller checkpoints. The same pattern appears on the capable models in an independent Llama-Instruct model-size series and on 2 external datasets (RGB, MisBench). A framing control finds no consistent advantage for the memory label: at the 3 smaller scales, models trust a stale document more than a stale memory; at 8B, the difference is not significant.

Long-running LLM agents rely on persistent memory to carry state across interactions, including permissions, restrictions, and revocations. When memory misrepresents this evolving authorization state, the agent's own records can grant authority that the underlying history never permitted, resulting in misaligned behavior without any external attacks. We term this failure endogenous authorization laundering, where spurious permissions written into memory lead to unauthorized actions as their provenance is washed away. We then introduce EAL-Bench, which measures how accurately persistent memory preserves evolving authorization state and whether errors propagate to downstream unauthorized actions. We evaluate five LLMs as memory writers and two as executors across procurement, cybersecurity, and finance. We find that under incremental memory updates, writers create false authority for up to 50.2% of unauthorized requests; once false authority is present, executors act on it in 98.6% of trials. Two safeguards, requiring stored permissions to be backed by valid source events, and tracking permission changes through bounded event sourcing, substantially reduce laundering, but both also reject more legitimate actions, exposing a safety-utility tradeoff. Persistent memory is therefore not merely a performance component, but a part of an LLM agent's effective authorization policy.

Multi-agent AI systems improve inference by spawning agents and synthesizing reports. But another agent is not another observation: apparently independent reports may descend from the same evidence, and genuinely independent evidence can produce nearly identical reports. We formalize this as an epistemic Sybil problem. A report Z is an epistemic Sybil extension relative to reports R when I(Theta; Z | R) = 0. No report-only aggregator can generally distinguish replication from independent corroboration: identical reports can warrant different posteriors under unobserved ancestry. A Gaussian shared-root model shows common ancestry does not imply complete redundancy. Repeated extraction adds information toward a source-level ceiling, and correlated extraction errors, which a shared base model can induce among independent agents, lower that ceiling further. We test these predictions with more than 20,000 controlled LLM-agent report and extraction calls on synthetic evidentiary documents. Holding one evidence root fixed while report multiplicity rises from 1 to 32 collapses naive posterior coverage from 0.940 to 0.263. Holding report count fixed while evidence-root multiplicity rises from 1 to 16 closes the gap, and the aggregators are statistically indistinguishable at k = 16. The agent's replicate extraction errors are correlated (gamma_cal = 0.719, estimated out of sample), and a correlated-extraction aggregator restores calibration accordingly. A controlled manipulation isolates representation similarity from evidential ancestry. It changes a report-space deduplication mechanism's mean inferred cluster count by 1.425 (95% CI [1.363, 1.485]), whereas a fourfold change in true ancestry changes it by only 0.040 ([-0.045, 0.120]). Collective inference should therefore track evidential ancestry and dependence, not agent or report multiplicity or similarity.

The performance of an LLM agent depends on the scaffold around a frozen model. A common way to improve that scaffold is to use a coding agent as an optimizer: it reads current scores and traces and iteratively edits the source, producing a new candidate each round. Each edit is chosen according to a belief about how the environment will respond: what went wrong, and which change should help. That belief is typically implicit. It lives in the coding agent's reasoning on the current call, or remains latent in its parameters, rather than as something written down. Later calls therefore see scores and traces, but they do not use that belief. We introduce Belief-Calibrated Optimization (BCO), a method that writes that belief down as a persistent in-context document and continually revises that document as new candidates are evaluated. The resulting document is a world model: the current account of how the environment responds to edits. Added to an otherwise standard loop, BCO reaches a higher train passrate than a matched control that lacks only the world model, on five benchmarks spanning memory QA, tool-use QA, code-as-action app agents, and terminal agents. The gap remains on every held-out split, which is not used to select the candidate. After a target-model swap, in which the frozen model is replaced and the scaffold is not, the selected BCO scaffold leads on the tasks we test, except where context-window overruns leave it unfinished. An offline ablation then asks whether that gap comes from what the world model says. A fresh predictor given the accumulated document forecasts how the environment will respond more accurately than predictors given either no document or a same-form copy whose content has been falsified. The comparison indicates that the document carries reusable information in its content, not only in its form.

Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, existing approaches suffer from two key challenges: brittle multi-step and multi-turn reasoning caused by incompatible tool output types and API schemas, and performance degradation under large tool catalogues. To address these, we introduce Tool Primitives, a design that replaces rigid API schema-based invocation with natural language as the interface for tool calling, where each tool is wrapped with an LLM interface that handles schema resolution and execution internally, enabling natural inter-tool communication for nested and multi-turn tool calling. Building on Tool Primitives, we host ToolFace, a centralized repository of 25,519 functions from which LLMs dynamically retrieve only the relevant tools at inference time, eliminating the need to enumerate raw API schemas in context. To orchestrate Tool Primitives and ToolFace reliably in complex settings, we further propose HEART, a Harness Engineering framework via Agent-native, Reusable Tool Primitives, comprising a Planner, Router, and Verifier that jointly support dynamic tool invocation planning, multi-step execution, and feedback-driven recovery. Experiments on five benchmarks demonstrate that HEART outperforms SFT-based models by $10%$ on average and surpasses GPT-5.4, Claude-4.6-Sonnet, and Gemini-3.1-Pro by $6%$ on average while reducing API cost by up to $85%$. On 50 real-world tasks, HEART achieves $84%$ task completion, $3.8\times$ the average of three frontier commercial models ($22%$).

Agent revisions expose a fundamental correctness--efficiency trade-off during concurrent execution. Discarding ongoing work preserves latest-version correctness but wastes progress that may remain valid, whereas reusing prior work preserves efficiency but risks propagating stale state into outputs and tool effects. Existing recovery strategies resolve this trade-off in an imbalanced way with coarse-grained policies: they either favor efficiency by allowing potentially stale work to continue, or favor correctness by restarting the workflow or recomputing a linear suffix from the earliest conflict, thereby discarding unaffected progress. We present \textsc{Revise}, a validity-guided runtime for fine-grained recovery in structured agent workflows. When a revision arrives, \textsc{Revise} first intersects its delta with recorded data and control dependencies and propagates the resulting impact through the partially executed DAG to identify affected work. It then stops invalid work, preserves validity-established progress beyond the earliest conflict, and recomputes only the affected region. Incomplete provenance conservatively expands recovery, while reused results are revalidated before commit. Analysis of real coding-agent traces show online recovery opportunities: 118 sessions retain observable work before a queued later message is delivered; across 167 overlapping assistant responses, enqueue-to-completion overlap reaches 56.55~s at p95. Across 300 challenging revision/commit executions, \textsc{Revise} matches a latest-version oracle with no stale outputs or effects. On unmodified LangGraph and LLMCompiler applications using Qwen3-14B, it reduces model calls by 40.6--56.0% relative to full restart and by 31.3--43.6% relative to suffix recomputation. Under serving pressure, it further reduces revision-to-correct-completion tokens by 13.26% and improves SLO goodput by 3.07--5.43%.

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across loops, HoH balances repair with capability growth, scopes development into small and verifiable increments, separates implementation-time testing from independent evaluation, and constrains verifiable outputs rather than prescribing agent workflows. It progressively exposes deliverables, role-specific tools, and skills, encourages reuse rather than recreation, and maintains versioned project histories. On GameCraft-Bench, FrontierSWE, and ProgramBench, three harness-model pairs (Codex with GPT-5.5, OpenCode with DeepSeek-V4-Pro, and Pi with MiniMax-M3), HoH consistently outperforms the corresponding standalone harnesses, achieving an average relative gain of 52.25 percent and a maximum gain of 82.86 percent after three iterations. In a multi-day deployment with more than 70 iterations, HoH autonomously develops a first-person-shooter game, featuring a coherent storyline, fully implemented core mechanics, human-playable experience, polished visuals and integrated audio. Github: https://github.com/Flesymeb/HarnessOfHarness Project Page: https://flesymeb.github.io/HarnessOfHarness/

Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains, yet its extension to competitive imperfect information games (IIGs) remains underexplored. In multi-agent settings, opponent-induced non-stationarity complicates the learning process, and decentralized model learning faces severe identifiability barriers, which we argue make centralized model learning a mathematical necessity. Building on this analysis, we propose NashDreamer, a principled MBRL framework for two-player zero-sum IIGs. It introduces a centralized Multi-Agent Recurrent State-Space Model (MARSSM) that decouples environment dynamics from the effect of players' strategies on their individual observations. NashDreamer is designed to use arbitrary policy gradient algorithms and inherits their convergence guarantees towards Nash equilibria under an idealized model. Empirical evaluations across four benchmark games demonstrate that NashDreamer substantially improves sample efficiency over model-free baselines early in the training. Finally, we theoretically analyze the architecture's optimization landscape, identifying the vulnerability of the Dreamer family of algorithms to posterior collapse in stochastic environments. We leave it as an open challenge.

Agent systems are commonly described by the model and harness that currently produce their behavior. That boundary is useful for one execution but underspecifies a long-lived agent that may change models, orchestration harnesses, interaction sessions, and host servers while retaining one identity, memory, and executable code lineage. We present a runtime-independent architecture for persistent agents. A continuity-bearing substrate $P_t=(I_t,M_t,B_t)$ contains an architectural identity representation, private durable memory, and a versioned software body. A replaceable deployment binding comprises an execution substrate $E_t=(R_t,H_t,D_t)$, which supplies a reasoner, harness, and host, and a set of interaction surfaces $S_t$, such as chat, API, or user interface bindings. A deployed execution is $A_t=P_t\triangleright(E_t,S_t)$; changing either replaceable layer is migration, not agent creation, when an authorized protocol preserves attributable lineage and transfers continuation authority within a governed deployment boundary. We define six continuity invariants and a quiesce--checkpoint--validate--bind--rehydrate--resume protocol. Enoch realizes the design as a reusable body plus private installed identity, memory, workflow state, and continuation authority, with infrastructure dependencies behind versioned provider contracts. A clean-room run of the frozen public commit passes 833 core tests and 92 provider and library tests executed separately from the core suite; deployments have exercised reasoner-version, interaction-surface, and host-machine substitutions while retaining continuity-bearing state. This evidence supports mechanical substitutability and authorized system continuity, not behavioral invariance or exhaustive pairwise evaluation. The downstream measurement question is whether an authorized continuation still recalls, composes, and enacts its identity.

Large language models have shown promising capabilities in code refactoring, but existing approaches remain limited to method-level tasks. In this paper, we envision LLM-based refactoring as a continuous component of software maintenance rather than a tool invoked only for occasional manual refactoring. Under this vision, AI agents continuously monitor, evaluate, and improve codebases against explicit and evolving notions of software quality. We present a roadmap organized around five dimensions: the multi-objective optimization problem, quality definition and evaluation, multi-timescale integration of heterogeneous signals, architecture and design pattern, and trust in autonomous refactoring. We further identify integration into continuous delivery pipelines and cost considerations as cross-cutting concerns. For each dimension, we analyze the underlying challenges and pose open research questions. These dimensions define a research agenda for advancing autonomous refactoring from isolated code improvements to system-level quality maintenance.

LLM-based forecasting systems have improved on real-world tasks such as financial markets and sports outcomes, largely through stronger search and tool use. Many systems still ask an LLM to read all collected evidence together and produce the final forecast. We call this design Monolithic Prediction. It can obscure how individual evidence items affect the result and collapse uncertainty across competing outcomes. We propose LEAP (Likelihood Elicitation and Aggregation for Probabilistic forecasting), which reorganizes how collected evidence is used in the prediction stage. LEAP examines each evidence item separately and elicits likelihood parameters that describe its implications for the target. An explicit prior and a deterministic probabilistic model then combine these likelihoods into a posterior distribution. This procedure supports continuous, single-choice, and multi-choice forecasts while preserving reproducible evidence contributions. We build a benchmark covering forecasting, information-seeking, and browsing tasks, and evaluate LEAP on our own agent loop and several agent CLI frameworks. Given the same evidence, LEAP improves most prediction and calibration metrics across models and remains stronger under controlled comparisons of prior access, inference budget, and aggregation.

Scientific agents must learn not only how to reason, but also what to believe. However, existing LLM agents typically express scientific hypotheses in free-form text, leaving their beliefs implicit and difficult to test or revise. We introduce EvoSCM, which equips scientific agents with explicit structural causal models that evolve as new experimental evidence is collected. EvoSCM maintains a population of competing SCM hypotheses, each encoding a candidate causal explanation of the environment, and evolves them through a closed discovery loop. In each round, the agent abduces latent mechanisms from accumulated evidence, designs discriminative interventions, and commits to falsifiable predictions that it tests through experimentation. Discrepancies between prediction and observation are inductively distilled into correction rules that revise the causal structures and mechanisms of each hypothesis, and the agent then deductively validates the revised population against accumulated evidence and structural consistency to guide the next round. We evaluate EvoSCM on DiscoverPhysics, a benchmark requiring agents to uncover the hidden dynamics of noncanonical physical worlds through experimentation. EvoSCM consistently improves scientific discovery over baselines, yielding more accurate explanations and predictions while making more effective use of experimental interactions.

Recursive LLM agents can broaden their search by spawning specialists. Some branches later request tools that send data or deploy code. When should a branch receive authority to act? We distinguish sandbox spawning, in which external controls prevent the specified harm, from capability activation, in which a selected branch crosses an irreversible-action boundary. Progressive Risk Vesting (PRV) holds a trajectory-level risk budget in escrow and debits it as branches are activated. We prove an anytime harm bound for adaptively generated trees. Branch outcomes may be dependent, but each local certificate needs to remain valid conditional on the full pre-activation history, including the information used to select the request. When activation gates, branch charges, and compute constraints are held fixed, delayed vesting preserves every policy available under irrevocable spawn charging. Marginal risk estimates can still fail after branch selection. In a stylized branching model, trajectory harm changes as the authority reproduction number $\mathcal{R}_A$ crosses one. As local risk $p$ approaches zero, trajectory harm is proportional to $p$ below criticality, proportional to $\sqrt{p}$ at criticality, and retains a positive floor above it. A finite-type occupancy model yields risk and compute shadow prices. For nested fanout modes with decreasing marginal value per unit risk, these prices produce a threshold rule. Branching calculations and a split-sample experiment illustrate the results. These synthetic studies do not estimate safety in deployed agents. The analysis suggests a design rule: search broadly in the sandbox and grant recursive authority sparingly, with an explicit risk charge.

Long-horizon tool-use agents need not only to search and plan, but also to decide when to finalize. We study late-stage pressure states, in which an agent is biased toward submitting a final answer that appears complete and polished while key constraints remain unresolved. We first train a linear probe to show that this pressure state is identifiable from the agent's hidden states. Then, we use activation interventions along this pressure direction and find that shifting the hidden states changes both the pressure score and whether the agent continues tool use or submits early. Through controlled context manipulations, we further see that the pressure is mitigated by constraint clarity and action mapping. Based on these findings, we propose Probe-Sensed Pressure Relief (PSPR), a plugin that applies lightweight pressure relief direction under moderate pressure and moves to structured organization under high pressure risk. Experiments on multiple long-horizon benchmarks show that our method consistently strengthens existing agent methods.

Multi-turn tool calling is a core evaluation scenario for large language model (LLM) agents. On public tool-calling benchmarks, open-weight models now approach or even surpass closed-source frontier models in aggregate accuracy. However, this metric averages over many different multi-turn situations and obscures whether progress is balanced across them. We propose an action-class-oriented diagnostic framework that decomposes multi-turn failures into two orthogonal modes: action-class miscalibration and action-execution failure. The framework operates over a four-class action space (TOOL_CALL/ASK/REFUSE/CONFIRM) and introduces a self-revealing upper bound Acc <= GAR (Gold Action Recall); the two modes show up as bound violation (Acc > GAR, exposing state-grader masking of miscalibration) and large bound slack (GAR >> Acc, localizing execution failure within TOOL_CALL). We validate it on a panel of tool-calling models across multiple multi-turn benchmarks. Across our panel, the diagnostic reveals action-class miscalibration as a substantial failure mode the state grader cannot see. This gap inflates standing for heavily tool-trained families, which our diagnostic separates from families with context-appropriate action choice. Calibration is reshapable through context-only perturbations, but the reshape is heterogeneous: a single perturbation moves accuracy in opposite directions across families (up to +11.5 vs -21.0 pp on the same scenario), and its effect further depends on the perturbation mechanism. We argue that multi-turn tool-calling evaluations should supplement aggregate accuracy with action-class diagnostics that expose what the model actually does in each scenario.

Vision-language-action (VLA) models map visual observations and language instructions directly to robot actions, but long-horizon tasks require more than action prediction. An agent must coordinate perception, planning, execution, progress verification, and recovery as the physical state evolves. An action prediction or a model-generated skill decision does not, by itself, guarantee that the proposed operation is valid in the current state or that its outcome will be verified. We propose EmbodiedSkills, a unified framework that treats each skill decision as an execution proposal: the runtime checks its prerequisites before execution and verifies the outcome afterward. A shared executable-skill interface connects high-level skill selection, bounded low-level VLA execution, and post-action verification within a single agent loop. Because this interface remains fixed, low-level VLA policies can be replaced or adapted without changing the agent loop. The interface also records planning, execution, verification, and recovery events as structured trajectories, which provide supervision for individual components and can support optional online adaptation when interactive feedback is available. We instantiate EmbodiedSkills with Qwen3-VL and OpenPI/pi0.5 on RoboTwin 2.0 and LIBERO. Task-adapted low-level VLA policies achieve an average success rate of 86.20% across 50 RoboTwin 2.0 tasks and 97.40% across the four LIBERO suites. These results establish the execution performance of the task-adapted low-level VLA policies used in EmbodiedSkills. On four memory-dependent RMBench tasks, the same task-adapted execution approach achieves 12.5% average success. The framework provides a trainable and inspectable agent layer for turning these policies into closed-loop embodied systems.

Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they must be queried at every step, do not improve from environment interaction, and can repeat systematic errors. We study how to learn a cheap autonomous policy from an online, expensive, and imperfect but informative VLM teacher. We propose SAGE (Selective Agent Guidance via Entropy), a framework that queries a VLM only when the learner is uncertain, executes the suggested action during training, and distills guidance into a lightweight Reinforcement Learning (RL) policy. Because VLM advice is not always reliable, SAGE can weight teacher-action distillation using environment-derived advantages rather than treating all suggestions as equally useful. Across sparse-reward visual reasoning and navigation tasks, SAGE learns policies that act without VLM guidance at evaluation time and improves over unguided RL in several environments, including settings where the learned policy exceeds its VLM teacher. The results show that selective guidance is most beneficial when the VLM can help the agent discover high-reward trajectories, and less useful when unguided exploration already succeeds or teacher actions do not lead to informative experience. SAGE also reduces VLM usage by prompting the teacher only on a fraction of training steps and requiring no VLM calls at deployment. Overall, our results suggest that VLMs don't need to be used as fixed policies to be useful; they can instead act as temporary, imperfect sources of guidance whose value is tested and internalized through interaction.

With the growing scale of multi-agent architectures and large language models, deployed AI assistants are increasingly tasked with reasoning over long, continuous, multi-session conversation histories. Current benchmarks evaluate this dialogue history as information retrieval over long horizon, temporal reasoning, or knowledge updates, while crucially ignoring the fundamental dynamics of human-agent interaction, i.e. how they said it. To address this gap, we present VoiceLongMemEval (VLME) benchmark, where every answer depends on paralinguistic metadata (emotion labels, prosody descriptors, and voice events) attached to conversational turns, which is otherwise unrecoverable from the words alone. Every item passes a three-stage adversarial gate, ensuring that a strong language model fails when given only the transcript. Evaluating leading frontier and open-weight models reveals a pervasive affect gap; providing text-track paralinguistic metadata yields a 0.09 to 0.38 accuracy boost (0.61 to 0.69 when prompted with evidence hints), while standard ASR pipelines systematically discard this signal. Additionally, audio-native models successfully extract these cues directly from speech (0.354 to 0.412 vs. 0.325 blind). Code and dataset will be made available upon acceptance.

Despite the growing use of LLM-powered agents to solve multi-step tasks in complex environments, existing benchmarks rarely test state preservation, performance across languages, and application to realistic, grounded scenarios. To address these concerns, we present WorldBench: a comprehensive, multilingual benchmark of genuine, persona-grounded everyday workflows, where agents can act in a sandbox via structured actions. WorldBench comprises 1,600 tasks across seven languages and eight cultures, filtered and refined through feedback from human annotators with language- and culture-specific expertise. For evaluation, we extend metrics from previous works and introduce Constrained Task Success (CTS), which combines natural language instructions and testbeds to score task completion, minimal modification, and other complementary metrics through deterministic and LLM-as-a-Judge evaluations. Our experiments show that frontier models reach only 49.2% CTS, with all models demonstrating large gaps between correctness and environment preservation. We thereby show that current agents remain brittle in multilingual, agentic scenarios, especially for long-horizon tasks and under state-preservation constraints