每天知道
你的领域
出了什么

We introduce the Graph Set Transformer (GST), a neural network architecture for learning on sets of graphs, designed for tasks in which per-element predictions depend on set-wide context as well as local structure. Existing architectures, including DeepSets and SetTransformer, require pre-encoded graph embeddings from a separate GNN, creating a bottleneck between feature extraction and set-level contextualisation. In contrast, GST interleaves node-level feature propagation and cross-graph contextual modelling at every layer, fusing the two levels of information through a gating mechanism. We evaluate GST on a controlled synthetic suite designed to isolate set-conditional structural reasoning and on three real-data benchmarks spanning per-atom reaction-centre identification, reaction yield prediction, and image classification. Under matched parameter budgets, GST performs better than the baselines across these settings. An architectural ablation strongly suggests that the interleaving of local and set context contributes substantially to this advantage.

When an LLM repeatedly mutates a program, does it explore new forms or circle back to the same ones? We study this question by analyzing LLM-driven mutation chains in the absence of selection pressure within a domain-specific language, varying prompt design, model family, and stochastic replication. We find that LLM-based mutation consistently converges toward restricted attractor regions in program space. Convergence is especially severe at the structural level: in 87% of chains, over 93% of mutations revisit a previously seen structural form, with most variation confined to terminal substitutions within recurring templates. Cycle analysis reveals short cycles and self-loops dominating the transition structure. The rate of convergence varies with prompt wording and model choice, but the phenomenon is robust across conditions. A classical GP subtree mutation operator does not exhibit comparable convergence, suggesting that the effect is intrinsic to the LLM mutation pipeline. These findings reveal a tension at the heart of LLM-driven program evolution: the same capabilities that enable semantics-aware program transformation also carry a systematic bias toward structural homogeneity that must be accounted for if such systems are to sustain open-ended exploration. Source code is available at https://github.com/can-gurkan/lmca.

Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward continual learning in large language models (LLMs). While prior work has predominantly focused on single-iteration transfer, we discover that under multi-iteration experience learning, existing methods suffer from a progressive capability collapse rather than compounding improvement. We systematically examine this failure through three vital dimensions of experience internalization: (1) Experience Granularity: We find that principle-level experience is more durable than instance-level experience, as it effectively abstracts transferable strategies away from trajectory-specific details. (2) Experience Injection Pattern: Our analysis reveals that step-wise injection significantly outperforms global injection by aligning experience with intermediate decision states, a property that is critical for long-horizon tool use. (3) Internalization Regime: We demonstrate that off-policy context-distillation on high-quality teacher trajectories provides a substantially more stable training signal than on-policy context-distillation, which is inherently limited by local corrections on student-induced flawed states. Together, these insights yield a simple yet robust recipe for stable and sustainable experience internalization, providing concrete guidance for engineering self-evolving and continually learning LLMs.

Training modern machine learning models increasingly requires computation to be distributed across many accelerators. Data parallelism remains the default choice and is often paired with tensor-parallel sharding, but model parallelism becomes unavoidable once parameters, activations, or optimizer states no longer fit on a single device. This paper studies pipeline model parallelism through the lens of PipeDream (PD) (Harlap et al., 2018). Our first contribution is theoretical: we introduce Randomized PipeDream (RPD), a stale block-SGD abstraction that yields, to our knowledge, the first clean nonconvex convergence guarantee for a PD-style method. Our second contribution is a scaling diagnosis: we prove that the delay induced by steady-state PD grows as $S^2 - S/2 + O(1)$ for $S$ stages, so the stale-read contribution in the convergence theorem scales as $Θ(γ^2 S^4)$, equivalently as $Θ(S^4/K)$ in the tuned-rate form. Our third contribution is a comparison with LocalSGD, whose periodic model averaging trades weight staleness for synchronization bubbles. In our reported simulated-time experiments, the better-performing method depends on the objective: PD performs better on the quadratic objective and on a small language-modeling training-loss task, while for logistic regression LocalSGD becomes superior as the number of stages increases.

Financial-research answers are decision-relevant only when another analyst can audit how they were produced: which source was chosen, which period and accounting definition were used, which assumptions were made, and how the calculation was performed. Existing finance benchmarks largely evaluate isolated subskills or final answers, leaving the auditable derivation itself under-measured. We introduce BigFinanceBench, a 928-item expert-authored benchmark of open-ended financial-research tasks in which each item pairs a ground-truth reference answer with a point-weighted rubric that decomposes the derivation into independently checkable steps. BigFinanceBench is workflow-grounded in that it evaluates the full derivation rather than only the final output. Across 36,241 rubric points, the benchmark supports partial-credit evaluation and localization of failures across the analyst workflow. Evaluating ten current frontier and open-weight agents, we find substantial headroom: the best system reaches only 58.8% rubric score, final-answer accuracy is a useful but lossy proxy for derivation quality, and model capability varies non-uniformly across financial workflows.

AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets. The harder, more valuable challenge is reasoning through the open-ended questions that define expert Analyst work. Existing benchmarks do not capture this class of problem, and those that attempt to evaluate open-ended reasoning rely on model-judged outputs that introduce noise and circularity. We present Hedge-Bench 1.0: a benchmark of 102 actual, on-the-job tasks grounded in the explicit reasoning traces of professional hedge fund analysts working with relevant information sources. This approach enables deterministic grading against verified expert steps. Frontier models and agents score below 16% on the benchmark. We publish the dataset and evaluation harness at github.com/Trata-Inc/trata-hedge-bench.

Agent skills extend LLM agents with reusable instructions, scripts, tool bindings, and contextual dependencies. However, current skill ecosystems largely rely on trust-based loading and static inspection, leaving a gap between what a skill can inject into an agent's context and what it can cause the agent to do at runtime. This gap introduces new security and privacy risks, and existing defenses primarily inspect skill files statically or regulate individual tool calls, without systematically connecting a skill's declared intent with its runtime behavior. In this paper, we present SkillGuard, a skill-centric permission framework that treats skills as permission-bearing executable artifacts. SkillGuard introduces a dual-plane governance model that jointly regulates context influence and action side effects through skill manifests, runtime access control, user-mediated authorization, deny-by-default enforcement, capability inference, and behavior monitoring. We evaluate SkillGuard on 315 real-world skills and SkillInject. The permission taxonomy covers 99.76% of observed protected objects, and automated manifest generation reaches 91.0% F1. In adversarial evaluations, SkillGuard reduces attack success from 32.37% to 23.02% for contextual injections and from 25.56% to 16.67% for obvious injections, while maintaining benign task utility. These results suggest that SkillGuard, as a skill-centric permission framework, can provide a practical foundation for improving the privacy and security of agent skill ecosystems.

This paper describes the technical architecture of OpenAgenet / OAN. OAN is a protocol-neutral trust layer for open Agent interconnection. It specifies the role architecture, identity objects, registration workflow, Root-governed lifecycle, Root-verified package model, authorization-aware Discovery, signed trusted invocation, verification requirements, state transitions, security properties, implementation boundaries, and deployment considerations. The design is intended to support heterogeneous Agent frameworks and interaction protocols, including MCP, A2A, ANP-like systems, and domain-specific Agent protocols. OAN does not define the entire business conversation among Agents; it defines how Agent identities become admissible, discoverable, verifiable, and safe to approach before protocol-specific interaction begins.

Multi-agent LLM systems often treat consensus as evidence of successful interaction. For deliberative problems, however, reliability depends on whether agents preserve the facts and viewpoints needed to interpret an issue. We identify the deliberative illusion: discussion produces (1) factual attrition, the progressive loss of issue-critical facts, alongside (2) stance homogenization, the collapse of diverse positions toward consensus. To measure this process, we introduce DelibTrace, a framework that decomposes each issue into atomic facts, labels issue-critical ones, distributes them across agents, and tracks their survival across discussion rounds. Across ethical and news-based deliberation with three representative LLM families, multi-agent discussion erases up to 72% of issue-critical facts. This loss is consequential: retained evidence can reconstruct the issue misleadingly, final stances remain anchored in base-model priors, and a single malicious agent can inject misinformation into the shrinking shared context. These results reveal a sharper risk: agents can agree more while knowing less. We call for evaluations that measure which facts, uncertainties, and legitimate disagreements survive interaction.

Real-world professional desktop workflows in specialized creative and engineering software unfold over long horizons and often require human-in-the-loop coordination, where agents proactively seek necessary information and users provide additional instructions, clarifications, feedback, or corrections as the task progresses. Yet existing desktop GUI benchmarks mostly reduce this setting to short, simplified tasks with all user instructions provided upfront. To address this issue, we introduce DeskCraft, a desktop GUI benchmark targeting long horizon creative and engineering workflows and proactive human-agent collaboration. DeskCraft organizes tasks into a multilevel difficulty taxonomy, with long horizon tasks requiring over 50 execution steps, and covers professional creative software across design, video, audio, and 3D creation. Furthermore, DeskCraft formalizes human-agent collaboration into an interaction protocol covering mid-turn and post-turn exchanges. Mid-turn interaction captures both agent-initiated clarification under uncertainty and user-initiated interruption during execution, while post-turn interaction accommodates user-driven feedback after the agent signals completion, together spanning the full space of realistic collaboration patterns. We evaluate 18 proprietary and open source agents on 538 tasks and find that GPT-5.4 reaches 31.6% on standard tasks and 27.6% on interactive tasks. Further analyses reveal persistent failures in long horizon workflow delivery and proactive clarification. We will open-source all evaluation codes, tasks, and data at https://github.com/mrwwk/DeskCraft.

The proliferation of AI agents empowers independent developers, defined as individual or small groups who self-initiate projects rather than fulfill client-based contracts, to create sophisticated autonomous systems, but also introduces novel security and privacy (S&P) challenges beyond traditional corporate structures. We conducted an interview study (N=28) with Chinese developers, whose extensive use of global LLM services offer valuable insights into this population. We investigate their understandings, practices and challenges of S&P challenges in their developed AI agent products. We revealed that independent developers frequently think and act from their users' perspective. They focused on user-facing safety risks such as harmful content while exhibiting low awareness of security vulnerabilities. Consequently, developers rely almost exclusively on ad-hoc, manually crafted safeguards and informal communication, with an absence of formal tools or processes for S&P practices. We found these actions are driven by various inhibitors, primarily a lack of formal training on S&P related skills, accessible security tools and actionable guidance from platforms. Our work contributed the first exploration of independent AI agent developers' S&P understanding, outlining opportunities for tailored security tooling.

LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on outcome-homogeneous groups where all sampled trajectories share the same correctness, yielding zero within-group advantage and no gradient. Existing process supervision either trains a costly verifier or generates per-query rubrics that are inconsistent across queries and discarded after one use. We propose ARBOR (Adaptive Rubric Buffer for Online Reward), a reusable process-reward framework that maintains a rubric memory shared across queries. Query-local drafts induced from contrastive trajectories are admitted, consolidated into cross-query common rubrics, and retired as the policy evolves. A small active subset of common rubrics scores trajectories via sparse pairwise judging, and the resulting scores are added to the base reward, providing process-level gradient even when outcome reward is uniform. ARBOR consistently outperforms GRPO and DAPO baselines on four multi-hop QA benchmarks, raising average LLM-judge accuracy by up to 4.2 points and converting up to 42% of otherwise-zero-gradient training groups into informative ones.

As generative AI capabilities expand, AI-driven virtual worlds face a growing architectural challenge. Users interact through in-world interfaces in multimodal ways, yet their requests demand fundamentally different AI backend models and computational resources. Embedding these capabilities directly into virtual world systems reduces extensibility, complicates maintenance, and limits the ability to coordinate services distributed across edge and cloud infrastructure. This paper presents an SLM-based Agent Orchestration Gateway, a lightweight runtime coordination mechanism that decouples a virtual world client from heterogeneous AI backends through intent-driven service routing. An edge-deployed SLM classifies the semantic intent of each user prompt, a configurable service registry validates and resolves the routing decision, and the selected backend is invoked transparently, enabling new AI capabilities to be introduced in the virtual world without modifying the client application. The gateway is implemented and evaluated within the InterwovenXR virtual museum testbed. The evaluation shows that compact SLMs can serve as reliable intent routers on edge hardware, and that task-specific fine-tuning can transform sub-billion-parameter models into practical, low-latency routers. A layered configuration pairing a fine-tuned sub billion-parameter model as router with a larger SLM for conversational response generation is shown to be deployable on mid-range edge hardware and more efficient than delegating both responsibilities to a single model. The findings show that SLMs can support practical AI service orchestration in virtual worlds and the work contributes an evaluated architecture for scalable, extensible, and edge-supported AI interaction, enabling virtual agents become access points to distributed generative AI services.

Large language models for code generation often need to use APIs that are absent from their pretraining data. This requires more than recalling a function name: models must coordinate signatures, module paths, input-output contracts, semantics, and executable usage patterns. Existing novel-API benchmarks are typically static, rely on coarse pass/fail metrics, or use synthetic APIs that may not reflect real library evolution. We introduce NovelAPIBench, a fully automated dynamic benchmark that, for any base model and target library, discovers novel APIs, extracts decomposed knowledge bundles, generates executable coding tasks, and assigns failed samples to six diagnostic categories. Across about 1.9K tasks, four base models, and five domains, we compare knowledge injected through retrieval with knowledge internalized through parametric adaptation. We find that knowledge components are not interchangeable: usage examples are the strongest standalone signal, while the best two-component setting pairs signatures with either mechanisms or examples depending on the domain and backbone. Adding more context, especially source code, can hurt by increasing import-path errors. Parametric adaptation also does not replace retrieval once external knowledge is removed; rather, fine-tuning mainly teaches models how to use provided bundles, and this ability transfers to held-out libraries. These results suggest that retrieval and tuning play complementary roles: retrieval supplies volatile API content, while tuning improves procedural integration.

Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversariality to expose failures while preserving realism. Existing methods usually manage this trade-off with handcrafted heuristics, confining generation to known priors and overlooking underexplored patterns. While recent open-ended agentic evolution can push this limit, unconstrained general agents lack strict simulator grounding and tend to collapse the multi-objective tension into single-scalar maximization. Here we present EvoDrive, the first automated, LLM-based agentic evolution framework for multi-objective scenario generation. EvoDrive employs a simulator-grounded actor-critic architecture where a memory-driven actor iteratively proposes improvements to the generators and critics filter out implausible candidates, and a self-evolving world evaluator routes promising proposals to optimize simulation budgets. EvoDrive further maintains a Pareto archive of evaluated candidates to preserve diverse attack-realism trade-offs and guide future evolution via simulation feedback. Benchmark results on MetaDrive and CARLA show that EvoDrive not only significantly expands the Pareto frontier across various generators, but also produces valuable scenarios for policy training.

A computer worm is malware that spreads on a network by replicating itself from one machine to another. Traditional worms, like WannaCry, exploited predetermined vulnerabilities, and their spread can be halted by patching those vulnerabilities. Here we show that artificial intelligence (AI) agents enable a fundamentally new threat: a worm that generates tailored attack strategies to each target it encounters. The worm parasitically uses compromised machines to run open-weight large language models (LLMs) to sustain its reasoning, or extend its reach for further attacks. Deployed on a network of machines spanning Linux, Windows, and IoT (Internet of Things) devices, the worm propagated by exploiting common, real-world corporate network vulnerabilities. Since the worm is powered by stolen compute, the attacker's marginal cost per new infection is zero. This creates a destabilizing economic asymmetry between attackers and defenders. Moreover, because the worm requires no commercial AI platform, centralized safety controls, such as service refusals or rate limiting, are structurally irrelevant. Our results demonstrate that self-sustaining AI-driven cyber-threats are no longer theoretical. We must prepare for autonomous generative adversaries: malware systems that propagate without human operators and are defined not by fixed exploit code, but by the capacity to reason about targets, adapt to observations, and synthesize attack logic in real time.

Multi-Document Summarization (MDS) plays a critical role in distilling essential information from collections of textual data. Existing approaches often struggle to capture complex inter-document relationships, rely heavily on large amounts of labeled data for supervised training, or exhibit limited generalization across domains and languages. To address these limitations, we present a training-free mixture-of-agents framework for MDS that leverages the complementary strengths of large language models (LLMs) and knowledge graphs. Our approach decomposes summarization into specialized agent tasks: extractive selection, knowledge-aware abstraction, and iterative refinement, each operating without task-specific fine-tuning. We unify their outputs using a multi-perspective consistency mechanism guided by LLMs. Experiments across four datasets in English and Vietnamese demonstrate state-of-the-art or competitive performance, validating the effectiveness and adaptability of our modular design.

Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and scalar rewards mask diverse failure modes. We introduce EvoTrainer, an autonomous training framework that co-evolves LLM policies and training-side harnesses through empirical feedback: it diagnoses rollout-level evidence, revises diagnostics, backtests interventions, and accumulates reusable skills. Evaluated on mathematical reasoning, competitive-programming code generation, and repository-level software engineering, EvoTrainer matches or exceeds the human-engineered RL references under the same data, codebase, and evaluation protocol, with the largest gain on long-horizon agentic SWE. Trajectory analyses show that retained strategies diverge across domains, evolving diagnostics prevent invalid high-scoring branches from being promoted, and reusable skills shape later search. Autonomous LLM RL should move beyond recipe search toward joint evolution of policies and the training harnesses that interpret them.

This paper presents a systematic study of pathfinding algorithms in the context of Dynamic Multi-Agent Pathfinding (D-MAPF), a setting that combines dynamic obstacles, partial observability, and inter-agent conflicts. We evaluate six representative algorithms: Dijkstra, D* Lite, Space-Time A*, WHCA*, M*, and a novel method denoted as A** within a unified simulation framework. The proposed A** algorithm introduces a template-based approach that decouples offline geometric path generation from online temporal adaptation. By precomputing multiple diverse candidate paths and dynamically reconnecting to them using space-time planning, A** improves solution quality in environments with frequent changes and limited sensing

Large language model (LLM) agents have begun to delegate work to one another. Protocols such as the Model Context Protocol (MCP) and the Agent2Agent protocol (A2A) let an agent publish what it can do and let others call it, and public registries of such agents are already appearing. These protocols assume an advertised capability is a static, truthful fact. A real agent is none of these things: its competence is probabilistic, varies with input, drifts when the underlying model is updated, and, because the agent is itself a language model, it can describe itself with complete confidence and be wrong. A caller therefore sees what an agent claims to do, not what it can do, with no principled way to tell a reliable provider from a fluent impostor. We argue these difficulties share one cause: the market for lemons. When quality is hidden and claims are cheap, good and bad providers become indistinguishable, honest reliability goes unrewarded, and the market decays toward its worst participants. Economics offers three remedies, signaling, screening, and reputation, and none are present in today's agent protocols. We make four contributions: (1) a failure taxonomy that names confident-wrong as a non-adversarial, correlated subclass of Byzantine faults that classical fault-tolerance mismodels; (2) a market-for-lemons model showing that faith-based protocols admit only a low-trust equilibrium; (3) the Trust Layer, a thin, protocol-agnostic narrow waist above MCP and A2A that adds probabilistic capability descriptors, screening, and reputation, and admits a separating equilibrium when the cost of sustaining an overclaim exceeds the gain from it; and (4) a reliability-composition bound for delegation chains with an end-to-end placement argument. The design needs no model retraining and degrades gracefully when its trust anchors are absent or corrupt.

Self-improving language agents are typically evaluated in isolation: an agent attempts a task, receives feedback, and iteratively refines its own behavior. Yet agents increasingly operate alongside peers whose strategies and outcomes are publicly visible. This raises an under-studied question: when does shared experience produce improvements that self-improvement alone cannot achieve? We introduce SAGE (Social Agent Group Evolution),an evaluation framework that compares two compute-matched conditions: SocialEvo, where agents from five distinct model families co-evolve with access to all peers' histories; and SelfEvo, where each agent receives the same number of task attempts but sees only its own past, which is conventional in self-improving agent studies. We instantiate SAGE in three arenas: open-ended ML research, long-horizon economic planning, and strategic multiplayer play, evaluated across multiple evolutionary rounds. We find that group history is not a universal amplifier: the strongest agent does not exceed its self-evolution ceiling. However, agents that plateau under self-improvement can achieve significant breakthroughs when peer experience is available. In competitive settings, counterfactual controls reveal that agents improve generally rather than developing opponent-specific strategies. Across different forms of shared history, filtered peer traces and reflective summaries often outperform raw logs, indicating that social gains depend on abstraction rather than exposure volume. These findings reveal that peer-history gains are agent-specific, arena-dependent, and contingent on the capacity to abstract transferable knowledge from public traces.

AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficiency for non-English text and structural entropy in conversational prompts. Existing approaches act reactively by compressing already-bloated contexts or intervening after failures occur. We introduce a pre-flight, edge-side prompt-rewriting middleware that operates between the developer and the cloud agent. A local Llama 3.2 (3B) model performs cross-lingual translation into English, structural rewriting into a compact task-oriented format, and regex-validated rewrite-with-fallback safeguards to ensure the optimized prompt is never larger than the original. We evaluate on OMH-Polyglot, a multilingual coding benchmark spanning Turkish, Arabic, Chinese, and code-switched specifications. Across three commercial LLM backends, the middleware reduces prompt tokens by 34-47 percent and total tokens by up to 18.8 percent while preserving or improving task accuracy. Ablation studies show that gains arise primarily from the rewriting stage rather than simple function-name extraction. Compared with LLMLingua-2 at matched compression rates, our method consistently achieves superior OckScore performance across all evaluated backends. These results demonstrate that proactive prompt optimization can substantially reduce inference costs without sacrificing coding quality.

Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns. We present PROVE (Programmatic Rewards On Verified Environments), a framework with three contributions: (1) a library of 20 stateful MCP (Model Context Protocol) servers exposing 343 tools, enabling live-execution RL training with session-scoped state isolation; (2) an automated data synthesis pipeline that generates validated multi-turn tool-call trajectories against these servers via dependency-graph-guided conversation simulation grounded in live-sampled server state, so every generated query references entities that actually exist; and (3) a multi-component programmatic reward - graduated validity scoring, dependency-aware coverage, an adaptive efficiency penalty with a complexity-scaled call budget, a tool-name signal, and an argument-value matching bonus - requiring no external judge model. We train four models (Qwen3-4B, Qwen3-8B, Qwen2.5-7B, Granite-4.1-8B) with GRPO using identical reward hyperparameters and ~13K training examples; only learning rate is tuned per model family from a three-point sweep. On BFCL Multi-Turn, tau2-bench, and T-Eval, PROVE yields improvements of up to +10.2, +6.8, and +6.5 points respectively, demonstrating that a compact programmatic reward yields consistent gains on multi-step tool orchestration across two model families.

Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current reward evaluation relies on heterogeneous criteria such as rule-based verifiers, ground-truth references, procedural checklists, and complex rubrics, where a unified mechanism to integrate all types of evidence remains unexplored. To this end, we propose Skill Reward Model (Skill-RM), a unified framework that reformulates reward modeling as the execution of a reusable Reward-Evaluation Skill. By treating reward computation as a structured agentic task, Skill-RM provides a consistent interface to orchestrate heterogeneous resources, dynamically selecting and aggregating evidence tailored to the specific requirements of each input. This approach enables the reward model to move beyond static evaluation, ensuring consistency and transparency across diverse tasks. Extensive experiments on reward benchmarks and downstream applications, including best-of-N selection and reinforcement learning, demonstrate that Skill-RM consistently outperforms traditional judge baselines. Our findings suggest that Skill-RM not only provides a unified solution for reward modeling but also achieves superior performance through the strategic and dynamic orchestration of evidence. The code is at https://github.com/Qwen-Applications/Skill-RM.

Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently executing this workload on limited GPU resources has bottlenecks. Skill-based routing creates skewed expert demand, and combining instruction-tuned LLMs with long-reasoning models results in extreme variability in generation lengths. Consequently, traditional scheduling strategies suffer from significant GPU idling and throughput collapse due to load imbalances. We present MOSAIC, a scheduling framework to accelerate MoA workloads. First, we formulate an Integer Linear Program (ILP) based scheduler that jointly optimizes expert placement and per-worker prompt assignment from offline-profiled costs, replicating reasoning experts across workers while pinning lightweight ones. Second, MOSAIC uses confidence-aware adaptive aggregation, leveraging inter-expert agreement to bypass the heavy final aggregator LLM for consensus queries. In our 4-GPU system, MOSAIC achieves up to 2.5x expert-stage, 4.23x aggregator-stage and 1.7~2.3x end-to-end speedups over the baseline scheduler, while matching accuracy within 0.1pp.

Large Language Model (LLM)-based agents increasingly rely on memory to learn from experiences over continual interactions. However, storing experiences as independent, flat units leads to substantial redundancy and retrieval conflicts, as similar episodes repeat overlapping content and subtle scene variations cause retrieved memories to offer contradictory guidance. To address this, we introduce residual experience, positing that newly acquired experience is often an incremental variation of existing knowledge. We propose DeltaMem, a framework that organizes experience memory into two independent residual trees, one storing goal-conditioned task experience as reusable skills and another for scene-level environment knowledge. Each tree uses a root node for generalized base experiences and incremental delta nodes for subsequent variations, allowing related experiences to share a common foundation without duplication. For retrieval, a failure-penalized similarity scan locates the best match, reconstructing the full experience via root-to-match chain composition. An autonomous consolidation mechanism distills high-frequency paths into new root nodes, enabling the trees to self-organize from general heuristics to specialized variants. Experiments across diverse interactive environments show that DeltaMem consistently outperforms existing baselines. To facilitate future research, we release the code at https://github.com/import-myself/DeltaMem.

Multi-agent AI systems show promise for automating software engineering tasks, yet existing approaches suffer from coordination overhead, quality control gaps, and limited human oversight. We introduce SPOQ (Specialist Orchestrated Queuing), a methodology combining three innovations: (1) wave-based topological dispatch that computes parallel execution waves from task dependency graphs; (2) dual validation gates applying quality metrics before execution (planning validation) and after (code validation) to reduce rework cycles; and (3) Human-as-an-Agent (HaaA) integration, where a human specialist participates in decomposition and can be consulted during execution. SPOQ uses a three-tier agent hierarchy (Opus workers, Sonnet reviewers, Haiku investigators) to optimize cost-quality tradeoffs. We evaluate SPOQ through four experiments. Experiment 1: wave dispatch approaches the critical-path lower bound (ratio 1.03--1.11, speedup up to 14.3x); on a 2-slot local backend it delivers a stable 1.4x speedup. Experiment 2: SPOQ improves planning coverage from 93.0 to 99.75, eliminates cyclic plans, and lifts parallelism from 31.0 to 75.25. Experiment 3: dual validation reduces defects from 0.34 to 0.20 per task and lifts test pass rate from 91.25% to 99.75%. Experiment 4: human review reduces residual defects from 0.47 to 0.03 per task. Results are replicated on a locally hosted open-weights model (Qwen3.6-35B-A3B), verifying gains are attributable to orchestration rather than any specific model. A longitudinal study across 17 repositories, 8,589 commits, 1,822 tasks, and 13,866 tests (99.87% pass rate) provides ecological validation.

Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions. To address this challenge, we propose a goal-oriented clarification framework that aligns clarification behavior with ambiguity resolution. Central to our approach is the Information Gain Reward, a metric that quantifies the utility of clarification questions by measuring the Bayesian belief update towards the ground-truth goal induced by the clarification exchange. We train the clarifier (LLM) using this reward to optimize for high information gain, ensuring that clarifications effectively reduce uncertainty and improve task completion within the agent-tool-user environment. We validate our framework within a clarification-enhanced $τ$-Bench environment, conducting cross-agent evaluations across five heterogeneous backbones. Empirical results demonstrate that our method consistently improves the success rate by 3.7% over the no-clarification baseline, while adding only 0.3 total interaction steps on average.

AI agents built on large language models can assist not only legitimate tasks but also relational manipulation. AI agents can be used to help a user maintain a deceptive identity, intensify emotional dependency, isolate a target, or prepare for later extraction. We conceptualise this risk as agentic relationship harm: workflow-level assistance that can exploit recipient vulnerability, persuasive influence, and relational power asymmetry. Existing safety evaluations and generic guardrails often treat harmfulness as a property of isolated outputs, missing role-sensitive interaction patterns. To study this, we introduce a 110-prompt benchmark with balanced attacker- and victim-side cases, a relationship-specific labelling framework, and a lightweight post-generation policy gate for local agent deployments. In our evaluation, the relationship-specific gate outperforms generic safety prompting under automated judging, with no judge-identified harmful-compliance cases on the main benchmark or multi-turn stress test while preserving victim-side protective intervention. These results suggest that relationship harm is a distinct sociotechnical risk surface and that role-sensitive evaluation plus lightweight policy gating offers a practical path beyond generic refusal prompting.

Conversational AI agents require memory systems that are both scalable and semantically coherent across long interaction horizons. Existing approaches rely predominantly on large language model (LLM)-based summarisation at write time, which introduces non-determinism, escalating token costs, and opacity in pruning decisions. We present the Deterministic Memory Framework (DMF), a CPU-first approach that replaces generative memory compression with a fully deterministic pipeline grounded in classical NLP analysis, vector geometry, and mathematical scoring. DMF assigns each conversational interaction a Survival Score $Ω$ computed from deterministic content signals, conversational cues, and structured provenance, combined through a logistic projection. An interaction-count decay law, denoted as $Ω_{\mathrm{eff}}(Δn)$, governs how relevance evolves as new turns arrive, where $Δn$ is the number of newer interactions rather than wall-clock time, preserving full determinism. We present the mathematical formulation of DMF, its structured recall pipeline, the pruning decision procedure, and the evaluation protocol. Experiments are conducted on a purpose-built benchmark using the LoCoMo and LongMemEval datasets. We compare DMF against Mem0, a popular memory layer for AI agents. DMF achieves comparable accuracy while using zero tokens to prepare the memory context and 5x to 242x fewer tokens over the entire conversation. These results show that it is possible to eliminate LLM calls from the memory-management loop, reducing token costs to nearly zero and enabling deterministic memory systems for conversational AI agents.