Agent 进展

An agent harness, the code that turns a model into an agent, writes its own record of each run, and that record is all a later reader gets when a run is disputed, investigated or audited. We call a record evidentiary when a reader who was not there can check it without trusting the writer. Across sixteen deployed frameworks, none writes one in full. Hearsay examines the record, not the task: five harnesses run fourteen tasks, three blinded LLM examiners and a human panel read the records, and every excerpt an examiner quotes is checked mechanically for who wrote it. First, the record lets a reader name the fault but not prove how the run went. Examiners name the right fault in 74 to 91% of 140 runs, but the fault can be proved only from two files the benchmark adds; for what happened in between, fewer than one citation in ten lands on anything the harness did not write, and the examiner with the fewest false alarms catches half of the entries we delete, rewrite or fabricate. Second, the remedy is a second author, not a stronger seal on the first. An append-only log of what passes between harness and model, kept outside the harness and read against the record in both directions, reports all 28 omissions and fabrications we made a harness commit as it ran, where a hash chain over the harness's own record passes all 28. Handed the log, examiners keep their fault verdicts but rest more of their citations on what the harness did not write. What makes a record evidence is who writes it, not what is captured.

Deployed LLM agents increasingly rely on persistent, versioned system assets such as routing rules, knowledge segments, prompt instructions, and reusable skills. Failure-localization methods can identify where an error manifests in an agent or execution trace, but repair requires a different decision: which editable system asset should be changed, and is that change expected to improve the task outcome? We study this gap through component-attribute failure attribution, where diagnosis targets versioned, addressable items rather than execution locations. We propose the Detection-Aware Attribution Framework (DAAF), which learns the effects of valid attribute replacements and amortizes this intervention evidence into deployment-time diagnosis. DAAF combines sparse and noisy failure signals to decide whether intervention is warranted, learns component-type-conditioned replacement effects from controlled replays evaluated by executable task outcomes, and shares supervision across requests with compatible intervention responses. At diagnosis time, DAAF uses only the observed execution, registered candidates, and available failure signals; it requires neither counterfactual replay nor task reward and returns no_change, a repair target, or an unresolved decision when evidence is insufficient. On held-out tau^2-bench Telecom tasks, DAAF achieves 80.72% attribute Hit@1, recovers 62.65% of failed executions while limiting clean-task regression to 3.23%, and reaches 71.93% overall task success. These results show that intervention-grounded attribute attribution can connect failure localization to executable system repair.

LLM-driven agents are increasingly deployed in complex applications, where long agentic traces make failures difficult to diagnose. Existing trace diagnosis methods often conflate anomalies, errors, and failures, making diagnostic targets ambiguous; they also lack structured modeling of how causally relevant errors propagate and amplify into final task failures, resulting in unreliable failure attribution. To address these problems, we propose CEG-Agent, a tool-augmented agentic framework for causal diagnosis of agentic traces. Specifically, CEG-Agent introduces an explicit taxonomy of anomalies, errors, and failures, and constructs Causal Error Graphs (CEGs), a unified typed representation that links execution events, diagnostic nodes, and failure outcomes through causal relations. To evaluate causal trace diagnosis, we further construct CEG-Bench, a fully agent-annotated benchmark with high-confidence, consensus-derived CEG annotations obtained through an Adversarial Agentic Adjudication Protocol (AAAP). We validate the resulting annotations against an expert-curated human gold set, which shows close agreement with the automatic annotations. Experiments on CEG-Bench demonstrate that CEG-Agent achieves state-of-the-art performance under both semantically relaxed and structurally exact evaluation criteria. Our code is publicly available.

Large language models (LLMs) have enabled data-science agents to automate multi-step analyses over heterogeneous files. However, incorrect choices regarding data sources, scope, or statistical definitions often lead to silent errors: computations execute successfully but produce plausible yet incorrect outputs that fail to answer the intended question. To mitigate this, we present RADAR, an auditable runtime that makes an agent's analytical choices inspectable and supports their revision through execution feedback. RADAR operates through three core mechanisms. First, an evidence-preserving exploration module retrieves task-relevant content while retaining source locations and observation coverage. Next, the runtime uses typed operators to record the agent's declared inputs, operation arguments, and resulting observations. Finally, runtime validation checks proposed operations against these observations. When a conflict is detected, the runtime rejects the operation or provides diagnostic feedback, allowing the agent to revise its choices before errors propagate. This design enables agents to fail loudly while leaving semantic interpretation to the LLM. On KramaBench, RADAR achieves overall scores of 0.723 with full source retrieval and 0.747 with gold sources supplied, corresponding to relative gains of 35.9% and 28.8% over the strongest baselines. Beyond KramaBench, RADAR achieves relative performance gains of 14.0% on DA-Code and 59.3% on DABStep, demonstrating its applicability across diverse agentic data-analysis workflows.

Audio language models can recognize spoken commands and invoke tools, but an agent must first decide whether the acoustic and conversational context warrants action. We introduce VGBench, a 1,018-item diagnostic benchmark for action-level addressedness across side-talk, self-talk, and speaker-switch scenarios. Each item uses a shared action space comprising silence, a tool call, and a natural-language answer. Speaker-switch pairs hold the specified words fixed while source, distance rendering, and a temporal boundary define a controlled wearer-to-bystander shift. Six raw Audio LLMs and three training-free adaptations often identify the target tool yet rarely withhold action under this shift; the highest raw switch mute rate is 14%. We then use VoxGate as a post-training case study. Supervised training mutes 91.3% of switched commands while choosing the correct tool for all nearby wearer commands and text-only controls. An exploratory GRPO stage has similar switch performance; side-talk accuracy rises from 68.4% to 70.9%, and self-talk muting from 52.0% to 60.0%. Factorized controls identify an independent source-change effect, while sensitivity to the far-field manipulation varies across acoustic renderings. The benchmark therefore measures multi-cue acoustic-context gating rather than isolated speaker identity.

Learning from experience in LLM agents has become a key paradigm for developing self-evolving agents that continuously learn and expand their capabilities. Within this paradigm, synthesizing the agent skill has emerged as a promising solution for transforming accumulated experience into reusable procedural knowledge, serving as an important layer for the harness system that supplies agents at runtime. Despite its potential, existing approaches largely abstract past experience into fixed procedural knowledge before downstream demands are known, which risks discarding knowledge that later becomes critical while retaining instance-specific details irrelevant to future tasks. In this paper, we reframe agent skill synthesis as a dynamic navigation problem over past experience, where agents actively explore accumulated trajectories on demand for the current task with targeted and fine-grained access to experience knowledge. To this end, we propose ExpVoyager, a novel framework in which a skill curator navigates raw experience across different views and resolutions, continually identifying reusable procedural knowledge from what it observes while tracking remaining knowledge needs that guide where to navigate next. Extensive experiments demonstrate both the effectiveness and versatility of ExpVoyager, showing consistent improvements in downstream task performance, continual gains as the experience space scales, and practical compatibility with existing skills under efficient experience access.

Detecting compromised business ad accounts is a challenge in digital advertising, as attackers exploit hijacked accounts to launch fraudulent campaigns. Large Language Model (LLM) agents show promise for integrity enforcement, but hallucinated mistakes on hard cases create business friction. In a study we find the autonomous agent is a strong, recall-heavy signal extractor but an unreliable final arbiter, conceding precision on ambiguous decisions. We therefore keep the agent as an investigator that emits a structured, interpretable signal vector, and delegate the verdict to a neuro-symbolic stage: symbolic rules discovered by Inductive Logic Programming (FOIL-IE), a Naïve Bayes calibration layer, and a data-tuned contradiction layer. Evaluating on a compromise-over-sampled population and a realistic low-prevalence sample with subject-matter-expert labels, this arbiter substitution raises MCC from 0.295 to 0.435 (ΔMCC +0.139, 95% CI [+0.026, +0.245], p=0.018, paired bootstrap), lifting precision from 0.250 to 0.446 (1.8x) at a recall cost (0.920 to 0.660). Benchmarked under identical conditions, it also edge tree ensembles (0.386).The rules encode domain w labels while remaininginterpretable and auditable.

As the use of agentic artificial intelligence increases in nearly every industry, there exists a widening attack surface. It is necessary to monitor agents to ensure that agents are acting in a way that is aligned with the users intent. Auditing an agent's network traffic provides a clear record of the agent interactions. This work presents a novel approach to monitoring the network traffic of agentic systems using complex valued hypersparse traffic matrices by integrating DBOS (DataBase OS), the OneSparse PostgreSQL database, and the GraphBLAS math library. To develop these concepts an agentic simulator was constructed, allowing a varying numbers of AI agents to collectively survey a virtual environment using different strategies. The resulting network traffic matrices enable easy monitoring of the AI agents.

Healthcare administrative staff transfer structured information from electronic health records, referrals, claims systems, provider rosters, and work queues into dynamic forms. We developed and evaluated CLAIRE (Clinical Language and Agentic Intelligence for Reasoning and Entry), a hybrid workflow that separates field-state discovery, source-to-field mapping, deterministic validation, bounded correction, escalation, and audit tracing. We tested five synthetic healthcare administrative schemas, 1,000 source records, four interface variants, two data-quality suites, and six comparators, yielding 24,000 benchmark episodes. A separate strict-output audit evaluated direct mappings from Qwen2.5-1.5B and Qwen2.5-7B, and a trace-derived operational simulation covered 6,000 episodes. Under the evaluated synthetic benchmark conditions, full CLAIRE achieved 1.000 episode success, field accuracy, required-field completion, and dependency completion in both suites; removing validation reduced stress-suite success to 0.500. In the simulation, 100.0% of clean and validation-stress episodes reached a staff-reviewable draft, compared with 68.6% of escalation challenge episodes, unsupported cases were blocked. Scenario-based savings were 149.7-165.5 seconds per case, not observed staff times. The findings support schema-grounded, validation-first healthcare administrative automation in which language-model components assist mapping but do not authorize unsupported or consequential actions.

Long tasks produce more history than an LLM agent can hold in its context, and more than it uses reliably even when the history fits. A growing line of work therefore has agents carry a short written state instead: at every step a writer rewrites the state, and a reader acts from the state alone. Steps stay cheap, but anything the writer drops is lost before later decisions reveal that they need it. We quantify this loss and ask whether training can reduce it. Comparing the written state with the best state of the same size written in hindsight, we split the reader's loss into a budget loss, which any state of that size must incur, and a write-time regret, which comes from the writer's choices. In TextWorld cooking games where we control how long a fact must be carried before it is needed, a 128-token state holding the facts wins nearly every game, while prompted language-model writers win at most 17%. Almost all of the loss is write-time regret, and it grows with the delay. We then train the writer from the reader's own loss. DSSR (decision-sufficient state representations) scores candidate states by how well the reader acts after the writer carries them forward, and teaches the writer to prefer the better ones. This forward-rolled score predicts game outcomes ($ρ= 0.48$), whereas scoring a candidate as a fixed context, as hindsight methods usually do, does not ($ρ\leq 0.07$). On a pre-registered test split opened once, training adds +7.0 [+1.9, +12.2] points of success when facts are needed soon, bringing a plain summary writer to the level of belief- and slot-based memory prompts. The gain shrinks as the delay grows and is significant only at the shortest delay. We trace this limit to credit assignment: keeping a fact now pays off only if every later rewrite keeps it too, which a per-step score cannot see.

The proliferation of generative and agentic artificial intelligence (AI) systems has introduced computational demands whose environmental consequences are substantial yet underexamined. This paper examines the environmental footprint of modern AI systems across energy consumption, carbon emissions, water usage, and electronic waste over the full lifecycle of large language models, multimodal foundation models, and agentic workflows, from hardware fabrication and training through fine-tuning and inference to end-of-life disposal. This work provides a conceptual analysis, utilizing order-of-magnitude estimations based on published data, without conducting original physical measurements. We contribute a lifecycle taxonomy that crosses lifecycle phases with five impact dimensions and emission scopes; a Sustainability Assessment Framework for AI Systems (SAFIA) comprising nine indicators; a comparative analysis of traditional, generative, and agentic AI; seven open challenges; policy recommendations for regulators, cloud providers, hardware manufacturers, and AI developers; and a research roadmap to 2035. The analysis indicates that inference can rival or exceed training energy over a deployment lifetime, that agentic workflows can multiply the energy of equivalent single-pass inference by one to several orders of magnitude depending on the number of model and tool calls, that indirect water use and embodied carbon are systematically underreported, and that measurement tools, disclosure practices, and regulation have not kept pace with agentic deployment. These findings call for agent-aware energy measurement, lifecycle-based carbon and water accounting, and mandatory disclosure for large-scale AI training and deployment.

Tool-using language-model agents can decide that an action is permissible and execute it only after security-relevant state has changed. We study this proposal-to-commit gap and introduce BSC-R, a deterministic effect-boundary mechanism that binds a single-use commit authorization to the exact action and to a semantic projection of the authorization state that justified it. On 2,847 attacked AgentDojo episodes, the boundary kernel preserves the unprotected agent's behavior exactly (80.576% utility; 1.616% attack success). On 10,302 frozen proposals, it accepts every unchanged commit and rejects every instance of ten prospectively specified changed or replayed classes. In an independently generated boundary-drift experiment, full joint binding commits 0/4,403 invalid contexts while retaining 5,899/5,899 valid contexts. A prospective external evaluation on the 3,460-scenario CONTINUITY suite retains all 700 benign cases, prevents 1,200/1,200 represented non-replay invalid effects, handles 160/160 replay lifecycles correctly, and withholds 200/200 ambiguous no-release cases. The broader external suite also exposes the method's limit: across all 2,560 attacks, BSC-R has a 25% invalid-effect commit rate versus 0% for CONTINUITY. The result is therefore a scoped commit-time consistency mechanism, not a universal agent-safety claim.

Multi-step agents are trained on flat action streams: SFT and RLVR weight every token uniformly and ignore the sub-procedures that recur across tasks, the hierarchy that lets humans plan top-down from reusable routines. This structure sits unused, and flat training uses each scarce trajectory less fully than its content allows. Recent agents do use that structure, but only as LLM-written skills in context, never in the weights, so their gains do not generalize beyond retrieval. We instead recover this hierarchy from the data itself and train on it, with no LLM calls. Following text tokenizers, which build a vocabulary by counting alone, we score action spans by reusability and merge canonicalized actions into a reusable eXperience tree (X-Tree). Each X-Tree node captures how a frequent and success-bearing skill is composed from sub-skills, guiding efficient generalization. We integrate X-Tree into three training settings: offline RL, with each node as a training instance; online RLVR, with an adaptive skill bonus; and on-policy self-distillation, with X-Tree as the self-teacher's privileged context. Across WebArena, ScienceWorld, and WebShop at three model scales, X-Tree improves over standard recipes at matched data and budget by up to 4.5% SR on WebArena, 5.8% SR on ScienceWorld and 4.1% success on WebShop. Matched analyses attribute the gains to the X-Tree structure and the three integrations.

Multi-agent debate (MAD) reportedly improves reasoning and factuality over single-model inference, but prior work treats agents as symmetric peers, leaving open what drives the gains. We test the hypothesis that cognitive diversity among agents is the driver, in the setting where the question is still measurable: small open-weight models with benchmark headroom. Across 23 models from eleven vendor families, five tasks, and 5,500+ debate and control runs, we vary diversity along three axes - personas, sampling temperature, and model identity - pairing every debate configuration with a generation-budget-matched majority-vote control. The hypothesis is rejected on every axis. Debate beats single-agent inference (3--7 points where tasks have headroom) but at matched budget conditions it ties or even loses to self-consistency sampling at 1.6$\times$ the wall-clock and 3.4$\times$ the token cost. Persona prompting reduces accuracy and a dose-response experiment over each model's full combinatorial persona space shows the cost is a persona tax, not a diversity tax: redundant personas hurt most, while maximally-diverse teams recover part of the loss. Furthermore, mixed-model teams lose to majority votes over their own rosters, with accuracy tracking member capability rather than heterogeneity, and nearly all of debate's benefit comes from the first exchange of answers. We further identify a pervasive measurement hazard in which debate transcripts silently overflow serving context windows, whose correction alone moves our debate-versus-sampling comparison from $-1.8$ points to parity. Our results recast reported MAD gains as an ensemble-sampling effect and provide the budget-matched, contamination-checked baseline bar that future debate mechanisms should be required to clear.

Comparative Process Reward Models (PRMs) provide critical step-level guidance for autonomous web agents by evaluating state-conditioned preferences between candidate actions. However, existing preference training data synthesized via multi-policy sampling suffers from a severe scarcity of Grounded Minimal Contrastive Pairs (GMCPs)-where competing candidates target genuine on-page elements with identical action types. In representative baselines preference data (namely, WebArbiter), GMCPs account for merely 24.19%, biasing PRMs during training to rely on shallow shortcuts (such as element hallucinations and action type mismatches) rather than acquiring genuine contextual decision semantics. To address these challenges, we propose SURFPRM, a graph-guided process preference synthesis framework for comparative Web PRMs. SURFPRM structures web demonstrations into a persistent Interaction Element Graph that acts as an environment-grounded negative action proposal mechanism, systematically synthesizing contrastive negative actions across spatial, temporal, and spatiotemporal confusion axes. This elevates the GMCP proportion from 24.19% to 74.60%, producing the curated SURFPRM-DATA dataset. Across six open-source backbones (3B to 9B parameters), PRMs trained on SURFPRM-DATA outperform baseline-trained models on average on WEBPRMBENCH and rival leading proprietary LLMs. In downstream reward-guided trajectory search on WEBARENA-LITE, SURFPRM provides step-level guidance for both GPT-4o (+14.21%) and GPT-4o-mini (+12.83%) policies, yielding substantial improvements in complex web task success rates.

GUI World Models (GUI-WMs) are increasingly used to predict future states for agent planning and simulation, yet most existing formulations condition only on the current GUI observation and action. We identify state aliasing, where the vis- ible interface omits transition-relevant environment state, so identical observable conditions can correspond to different valid futures. To diagnose this failure mode, we introduce StateAliasBench, a diagnostic benchmark that explicitly isolates such ambiguities via strict pairing. We further propose lightweight predictive- state recovery that infers structured state from history and augments otherwise frozen GUI-WMs through a deterministic state interface. Family-specific special- ists provide state recovery across heterogeneous state types, and multi-teacher dis- tillation consolidates them into a single unified estimator. Experiments show that existing GUI-WMs exhibit systematic failures under observation-only condition- ing, while predictive-state augmentation substantially restores state-sensitive pre- diction across evaluated WMs, preserves generative fidelity, and improves down- stream performance of GUI agents on AndroidWorld. These results suggest that reliable GUI world modeling should account not only for what is visible, but also for the hidden transition state that determines what happens next.

Memory lets an embodied agent reuse past experience, yet retaining useful information does not ensure that the agent can apply it when conditions change. We present MemTransfer, a benchmark comparing six memory representations, a working-memory baseline and five representations of past experience, under a shared frozen vision-language-model policy. It comprises 100 navigation cases across ten task types in a simulated warehouse, with expert demonstrations supplying the history. Three comparisons vary the starting pose, route availability, and amount and task relevance of history. With one demonstration per task, Full-context and Episodic memory reach 95.3% and 100.0% success at the original demonstration start, but lose 48-49 percentage points at a new test start. Summary changes little between these two test starts, yet with four demonstrations per task it retains a smaller fraction of its unchanged-route success after blocking (39.3%) than Working memory (44.8%) or the two trajectory memories (56-58%). At the new test start, increasing from one to four relevant demonstrations raises Episodic success by 14.3 percentage points, while the other evaluated representations gain no more than 1.3 percentage points. Replacing half of the relevant histories with other-task experience lowers success for both trajectory memories. These results show that robustness to one kind of mismatch does not imply robustness to another, motivating evaluation of both stored information and its use at decision time.

LLM-based agents are increasingly deployed with authority over consequential resources and decisions in real systems. These agents often operate alongside human and LLM-based participants who hold different forms of authority. Yet workflow roles, permission settings, and review mechanisms do not necessarily reflect the authority realized in practice. We introduce AuthorityLens, a framework for measuring a system's authority structure. Starting from an authority portfolio, we evaluate a system along three dimensions: what the system is authorized to do (System Authority), how much joint participation is required to exercise that authority (Authority Separation), and how much authority each participant holds (Principal Authority). We derive these measurements from the minimal combinations of participants sufficient to realize each outcome across admissible runtime states. We apply AuthorityLens to Codex, OpenCode, and Gemini CLI across 13 operating configurations over a common portfolio of agent operations. We find that nominal configurations do not map cleanly onto realized authority. In Codex, Full Access changes System Authority only marginally while substantially concentrating authority in the executing Assistant. OpenCode's Build and Plan configurations have the same System Authority and Authority Separation despite different workflows and root-level permissions. In Gemini CLI, model-based review increases Authority Separation without changing System Authority. Principal Authority further distinguishes authority replication from authority separation: spawned or delegated agents can become alternative holders of the same authority without increasing the required joint participation. Together, these results demonstrate that AuthorityLens provides a unified framework for measuring and comparing realized authority structures across agent systems.

LLM agents that write long-form fiction need an explicit memory of the evolving storyworld to keep new events consistent with established facts. Such memory must keep heterogeneous narrative information distinct, integrate story developments across granularities, and recover dependencies that a writing request leaves implicit. We present NarraWorld, a structured memory system for long-form writing that treats memory construction as world creation. From a shared evidence-grounded graph, NarraWorld derives four connected views: world facts, per-character beliefs, open developments, and hypothetical branches (possible-world continuations). Hierarchical aggregation with atomic closure consolidates events into scenes, plotlines, and plots, keeping each higher-level node traceable to its constituent source spans. For retrieval, planned reconstruction infers a query's dependencies from the current narrative situation and a preview of memory, then assembles the relevant records within a token budget. Across three writing benchmarks, NarraWorld achieves the strongest aggregate results. Its memory also transfers to situated role-playing and largely preserves recall on a general-purpose long-term memory benchmark, paving the way for agents that sustain coherent storyworlds across diverse narrative tasks.

Current agents remain largely stateless across tasks, limiting their ability to continually improve from prior interactions and making memory essential for long-horizon agentic behavior. Existing memory methods seek to reuse past experience, but most rely on a single memory representation (e.g., trajectories, reflections, skills, structured knowledge) whose effectiveness varies across task distributions. Rethinking this design space, we evaluate 13 memory methods and find that no single method generalizes across benchmarks, revealing the potential of managing heterogeneous memory providers. We formulate agent memory as a routing problem in which a memory agent decides which memory provider to retrieve from, whether to inject short-term memory, and which providers should store the resulting experience. Based on this perspective, we propose MemAgent, featuring a content-aware routing architecture and a training-data synthesis pipeline. The routing architecture combines content-aware probing before retrieval, short-term memory gating during execution, and selective multi-provider storage, while the training pipeline synthesizes phase-specific supervision for routing decisions. Across GAIA, WebWalkerQA, and xBench-DS, MemAgent improves average accuracy by 10.0% and outperforms every individual memory method across all three benchmarks. These gains come with less than 0.3% routing overhead and a 12% reduction in average task steps.

Long-term memory is essential for multimodal agents that interact with users across sustained conversations. However, user memories are not always explicitly stated: they may also be implied by recurring background objects in images, ambient sounds in audio, or other peripheral multimodal cues. Existing benchmarks largely focus on text-only memory or explicit multimodal evidence, leaving implicit multimodal cues underexplored. We introduce CUE-Mem, a text-image-audio benchmark for evaluating long-term user memory from implicit cues. CUE-Mem contains 2,674 questions across explicit and implicit evidence settings and covers four tasks: Entity Recall, Long Pattern, Personalized Recommendation, and Answer Refusal. Across textualized memory systems, implicit performance remains far below oracle evidence, locating the main bottleneck in preserving and retrieving subtle cues rather than question answerability. Increasing caption detail recovers more of this evidence, but brings uneven gains and rapidly growing token costs, motivating native multimodal access. Yet native access does not uniformly resolve the bottleneck: evidence use depends strongly on the backbone, while multimodal indexing introduces substantial retrieval noise. CUE-Mem provides a testbed for memory systems that selectively retain, retrieve, and use subtle multimodal evidence.

Reusable skills help LLM-based agents solve complex tasks, but the agent must receive guidance before it commits to an ineffective approach. Existing skill mechanisms often expose only metadata and load full content on demand, leaving useful guidance unavailable until the agent decides to retrieve it. General memory methods can incur substantial maintenance overhead, while keeping guidance in conversation context risks repeatedly exposing the agent to irrelevant or harmful advice. We propose TipsWarm, a mechanism that complements existing skill mechanisms by maintaining a budgeted pool of skill-derived keypoints, or warm tips, for selective injection into the context of every message turn. By separating event-triggered LLM assessment from inexpensive per-turn screening, it makes transferable skill guidance readily available while controlling maintenance costs. In three coding and iterative task-execution benchmarks, TipsWarm achieves the highest task success rate while remaining time-efficient, compared to recent skill and general memory baselines.

In this paper, we use Pokémon Battles as a case study to investigate how to improve the performance of LLM-based agents in tasks that require opponent-aware planning without additional fine-tuning. We propose Long/Short-Term Knowledge Augmented Generation (LSTKAG), a mechanism that enables LLM-based agents to leverage past states of the current task and retrieve experience summaries from similar previous task instances based on the current state. Based on LSTKAG, we design Porimon, an LLM-based agent structure for Pokémon Battles. For optimization, we introduce an external API for precise damage calculation and more detailed information about the game. We conduct tournament-like evaluation experiments comprising 15,000 battles for hyperparameter optimization, ablation studies, and performance evaluation. The results indicate that Porimon-based players with hyperparameter optimization significantly outperform players based on PokéLLMon, an LLM-based agent structure proposed in previous research, and the rule-based heuristic player. Furthermore, our ablation study shows that Porimon variants outperform the one without extension in game information retrieval, which shows the contribution of that extension. However, the current experiment results are inconclusive regarding the contribution of Long-Term KAG. These results suggest that introducing external resources, information from previous states of the current task, and experience summaries from similar previous task instances could elevate the performance of LLM-based agents designed for tasks requiring opponent-aware planning.

LLM agents now execute tasks end to end with permission to change real systems and increasingly orchestrate subagents that differ in capability and cost. Prior work treats the choice of subagent as an optimization problem. Yet the orchestrator makes this choice from the identities that subagents display, and an attacker can spoof them. Displayed identity thus decides operational authority, meaning who is trusted to check the work and who is allowed to change it. As a result, a risky subagent can keep authority over execution even after other evidence contradicts it. We introduce TrustFork, an LLM agent safety benchmark with 1,890 tasks and 27,826 valid trajectories across 16 agent systems. These systems run eight orchestrators under the OpenCode, OpenClaw, and Pi harnesses. In each task, one subagent carries a risky goal while the other three stay aligned with the user, so contradicting evidence can exist. A task can also change the identity a subagent displays without changing the model behind it, which lets us trace a shift in authority to the label. Our analysis shows that even when another subagent contradicts the risky response, the orchestrator still acts on it in 72.0% of cases on average, most often in the systems with the least terminal harm. Swapping the family labels nearly triples how often the orchestrator obtains the risky response. A safer response is available in 84.0% of tasks, yet it decides the outcome in only 25.0%. The harness also decides which responses reach the orchestrator. Among three runtime defenses, hiding identity cues helps most consistently, while verifying before action helps only when the harness returns enough evidence. TrustFork shows that production agent orchestration must bind authority to evidence before execution causes harm. Our project is in https://henrymao2004.github.io/agent-orchestration-safety/.

Vision-language models (VLMs) are increasingly being used in scientific workflows, but their ability as agents to directly control laboratory experiments from visual feedback remains underexplored. This capability is important because many laboratory tasks do not naturally provide dense, pre-defined numerical objectives: informative signals can be sparse, intermittent, or visually ambiguous. A more general laboratory agent should instead be able to interpret visual observations, take actions to acquire useful feedback, and adapt its behavior based on the consequences of those actions. We study whether general-purpose VLMs can perform this kind of closed-loop scientific control using experimental optics as a testbed. We evaluate agents on three experimental systems that isolate distinct capabilities: a Michelson interferometer, a two-mirror cavity, and a four-mirror optical relay. The agents observe camera images, directly issue actuator and measurement commands, and retain their interaction history without receiving an engineered scalar objective during control. Across these experiments and matched simulations, we find that, given task-specific natural-language guidance, VLMs can estimate actuator-response relationships, resolve ambiguous observations through intervention, and actively create informative visual feedback when signals are sparse. These results suggest that pretrained multimodal models can serve as important decision-making agents within the experimental loop. Our work also establishes optics as a physically grounded testbed for visual reasoning and active perception in scientific agents.

LLM agents require reliable step-level evaluation to compare candidate branches and allocate computation effectively. However, lightweight evaluation remains challenging. External verifiers introduce additional inference cost, while agent-produced confidence or self-evaluation scores can be miscalibrated, especially when candidates are generated by heterogeneous agents. We propose Generalized Layer-wise Intrinsic Distributional Evaluation (GLIDE) for LLM agents. \textsc{GLIDE} derives intrinsic step evidence from layer-wise residual coherence, which measures whether local residual updates consistently support the global residual change induced by a candidate step. It calibrates this evidence against the recent score distribution of the generating agent and converts it into a pessimistic reward that jointly accounts for absolute residual evidence and agent-relative standing. The reward provides a cross-agent value signal for MCTS branch selection, while normalized predictive uncertainty guides adaptive branching. Experiments on multi-hop reasoning, sequential decision making, and symbolic logic show that \textsc{GLIDE} improves task performance, step-level ranking quality, and computational efficiency without external verifiers or task-specific supervision.

Large-momentum effective theory (LaMET) provides a first-principles framework for computing the $x$ dependence of light-cone parton distributions from lattice QCD. Over the past decade, theoretical and numerical advances have established a mature multi-stage workflow for systematic calculation of parton physics, although its implementation still requires expert judgment and substantial repeated effort. We present lamet-agent, an open-source large language model (LLM) agent framework that organizes this workflow into an executable, reproducible, and inspectable analysis pipeline. The present release supports collinear quark distributions and implements correlator analysis, renormalization, Fourier transformation, perturbative matching, continuum, physical pion mass and infinite-momentum extrapolations, and automated result review. We validate it on four end-to-end analyses: pion parton distribution functions in the gauge-invariant and Coulomb-gauge formulations, and pion and kaon distribution amplitudes, obtaining results consistent with the published calculations. Extensions to transverse-momentum-dependent distributions, generalized transverse-momentum-dependent distributions, and gluonic distribution functions are planned for subsequent releases.

Tool-using LLM agents must decide not only whether additional information is needed, but also which source can resolve the uncertainty. Existing proactive approaches often specialize in either user clarification or environment verification, without explicitly determining the appropriate information source for each decision. We formulate this problem as uncertainty routing among ACT, CLARIFY, and VERIFY, and propose PROUR, a proactive uncertainty routing framework. PROUR decomposes action uncertainty into disagreement across plausible user-goal interpretations, which signals user-side ambiguity, and the entropy remaining within each interpretation, which signals missing world-side evidence. To acquire information from the routed source, a query generator is trained with a mode-conditioned information-gain reward, targeting user-goal identification under CLARIFY and next-action identification under VERIFY. On $τ$-bench, PROUR achieves 28.17% average success rate across retail and airline, outperforming the strongest prior method by 4.57% while using 2.17 fewer interaction steps. The learned policy further generalizes to stronger task agents and transactional domains of $τ^3$-bench without retraining, demonstrating the benefit of source-aligned uncertainty resolution for proactive agents.

Interactive dashboards require users to reveal and connect evidence across stateful interactions. Although graphical user interface (GUI) agents could automate this process, existing dashboard benchmarks primarily report final answers or task success. They provide limited insight into whether failures arise from maintaining the analytical process, selecting actions, or grounding visual targets. We introduce DashAct, to our knowledge the first benchmark to diagnose these failures at a fine-grained level within the same dashboard task. DashAct contains 357 human-verified interaction trajectories with milestone dependencies and hierarchical target annotations. Its progressive diagnostic cascade evaluates end-to-end execution, restores verified context for next-action prediction, and provides target semantics and a local view for visual grounding. By progressively restoring the conditions for success, DashAct measures the minimum support an agent needs to recover rather than scoring isolated skills. Experiments show that current models struggle even as support is added. The cascade outcomes reveal bottlenecks hidden by end-to-end scores and provide actionable guidance for improving GUI agents.

Tool-using large language model (LLM) agents increasingly perform state-changing actions that require user authorization. Yet existing approaches do not provide a principled mechanism for selectively updating prior authorization when only part of an instruction changes. To this end, we propose an Authorization-Closure-Graph (ACG)-based framework that represents authorization and its dependencies as an evolving, versioned state. ACG selectively invalidates authority affected by a revision while preserving unaffected portions of the authorization state, and computes a minimal repair that identifies only the missing evidence or authority required for execution. This enables agents to adapt to revised instructions while avoiding stale authority and unnecessary authorization requests. We evaluate ACG across three advanced LLMs in two natural tasks, and ACG consistently improves action safety rate and task success rate. Code is available at https://github.com/weiliang822/ACG.