NeurIPS 2026 论文列表

Recent development of large language models (LLMs) has empowered multi-agent systems (MAS) through external skills and inter-agent discussion to solve complex tasks. Although such a paradigm improves the capability of LLM systems, it also introduces substantial efficiency overhead. Existing approaches mainly reduce this overhead through software-level optimization. However, these methods overlook how to exploit the graph-level structure of MAS discussion and its suitability for hardware-aware acceleration, thus causing latency, especially when the number of agents, discussion rounds, or concurrent sessions increases. In this paper, we propose FASD, an FPGA-algorithm co-design framework for acceleration towards graph dynamic system agent discussion. We argue that MAS discussion can be formed as a graph-coupled dynamical system and thus agent activation pruning can be optimized through phase-coupled dynamics method. Based on these insights, we designed the FPGA-aware optimization for the problem. FASD mainly consists of the following parts. Firstly, we profile representative MAS workflows and construct a phase profile for dynamic system modeling. Secondly, the hardware-friendly optimization progress, given the profile, is implemented on FPGA. Through extensive experiments on multi-agent discussion workloads, we demonstrate that FASD improves discussion efficiency while preserving task performance, with stronger benefits as the agent graph becomes larger and more complex.

Reinforcement learning (RL) has demonstrated success in post-training large language models (LLMs) as agents for tasks such as computer use, tool calling, and coding. However, exploration remains a central challenge in RL for LLM agents, especially as they operate in language-action spaces with complex observations and sparse rewards. In this work, we address exploration for LLM agents by leveraging the ability of LLMs to plan and reason in language about the environment to shift exploration from low-level actions to higher-level language strategies. We thus propose Strategy-Guided Exploration (SGE), which first generates a concise natural-language strategy that describes what to do to make progress toward the goal, and then generates environment actions conditioned on that strategy. By exploring in the space of strategies rather than the space of actions, SGE induces structured and diverse exploration that targets different environment outcomes. To increase strategy diversity during RL, SGE introduces mixed-temperature sampling, which explores diverse strategies in parallel, along with a strategy reflection process that grounds strategy generation on the outcomes of previous strategies in the environment. Across UI interaction, tool-calling, coding, and embodied agent environments, SGE consistently outperforms exploration-focused RL baselines, improving both learning efficiency and final performance. We show that SGE enables the agent to learn to solve tasks too difficult for the base model.

Advancing spatial intelligence in Multimodal Large Language Models (MLLMs) is bottlenecked by the scarcity of complex, scalable 3D question-answer (QA) data. While manual annotation is labor-intensive, directly utilizing LLMs to synthesize these QA pairs often fails due to their inherent deficiencies in spatial and geometric computation. We introduce $\textbf{Exemplar2VQA}$, a scalable exemplar-driven visual question answering generation framework that rapidly synthesizes large-scale spatial QA pairs in simulated environments via multi-agent coding. By equipping collaborative agents with a meticulously designed library of geometric utilities, Exemplar2VQA bypasses LLMs' spatial reasoning flaws through deterministic code execution. Crucially, the framework exhibits remarkable versatility: taking diverse static object-centric spatial query templates as exemplars, it seamlessly and autonomously scales them into massive, high-fidelity synthetic datasets. Fine-tuning Qwen2.5-VL (3B/7B) exclusively on Exemplar2VQA-generated synthetic indoor data yields significant performance improvements across various diverse benchmarks. Furthermore, its effectiveness is not limited to in-domain indoor datasets but also robustly extends to outdoor and mixed-scene benchmarks. These results establish Exemplar2VQA as a scalable and powerful paradigm for bridging the sim-to-real gap in Embodied AI. The code will be available upon acceptance.

Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability remains under-evaluated, largely because existing benchmarks do not provide a systematic way to assess memory mechanisms. In this paper, we study agent memory from a self-evolving perspective and introduce \texttt{EvoMemBench}, a unified benchmark organized along two axes: memory scope (in-episode vs.cross-episode) and memory content (knowledge-oriented vs.execution-oriented). We compare 15 representative memory methods with strong long-context baselines under a standardized protocol. Results show that current memory systems are still far from a general solution: long-context baselines remain highly competitive, memory helps most when the current context is insufficient or tasks are difficult, and no single memory form works consistently across all settings. Retrieval-based methods remain strong for knowledge-intensive settings, whereas procedural and long-term memory methods are more effective for execution-oriented tasks when their stored experience matches the task structure. We hope EvoMemBench facilitates future research on more effective memory systems for LLM-based agents. Our code is available at \url{https://anonymous.4open.science/r/EvoMemBench-2}.

Human experts can accumulate experience from open-ended and complex inspection tasks, thereby continually improving their inspection capabilities. Actually, industrial hardware inspection faces challenges including open-set defect categories, complex defects (tiny, high-gloss, low-light, or blurred), high inference cost, and difficulty in accumulating experience post-deployment. Existing end-to-end inspection methods typically couple image restoration with defect recognition in a single forward pass, limiting generalization to unseen components or composite defects; cascade “restore-then-detect” approaches often rely on static preprocessing, hindering adaptive adjustment based on scenario, defect morphology, and historical failures. To address this, we propose EvoInspect, the first memory-enhanced multi-modal multi-agent framework for industrial defect object detection. It leverages a multi-modal agentic memory mechanism to distill self-evolving scenario-specific Defect Detail Restoration decisions and dynamically grounded trajectories, enabling “accumulating experience like human experts.” Specifically, (1) we introduce a dynamic Defect Detail Restoration strategy, including adaptive slicing for tiny defects, highlight suppression, low-light enhancement, super-resolution, and binarization, combined with a coarse-to-fine token-efficient grounding mechanism for efficient defect capture; (2) we design a dual-channel distillation mechanism unifying restoration and detection (perception and execution) experience, incorporating both successful and failed validation trajectories to support system self-evolution. Experiments on bearing surfaces, PCBs, solar electroluminescence (solar EL), and magnetic tile datasets show that EvoInspect consistently outperforms strong baselines in defect localization recall, inference accuracy, while demonstrating cross-scenario adaptability and offline continual improvement.

Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assessment. This fails to capture whether agents can maintain executable artifacts as requirements evolve. We introduce EvoCode-Bench, a benchmark of 26 stateful coding tasks spanning 227 evaluated rounds. Each task preserves the agent's workspace across 5--15 rounds, expresses requirements through observable behavior, and uses cumulative executable tests to check both new requirements and regressions against still-active prior ones. We evaluate 13 coding agents with two complementary metrics: MT@4, a four-attempt fail-stop multi-round score, and SR, a single-round score from a reference-completed prior state. For most agents, SR exceeds MT@4 by 22--40 points, indicating that isolated instruction-following does not imply persistent reliability. The gap also changes model rankings: the highest-SR agent (78.9) ranks only third in persistent execution (44.0 MT@4). Even the strongest agents achieve only \~50\% success on multi-turn metrics, and aggregate pass rate drops below half of round-1 performance by round~5. Failure analysis reveals tier-dependent behavior: weaker agents fail early, while stronger agents survive long enough to expose specification-tracking and regression failures. These results show that single-round and persistent multi-turn coding evaluate different capability dimensions. We release the benchmark data and Harbor multi-turn infrastructure.

Real-world scenes often contain static, slow, and fast components within the same field of view. Frame cameras are inherently inefficient in this setting, as their global exposure and fixed sampling must follow the fastest motion and therefore oversample the rest of the scene. Event cameras provide asynchronous local sensing, but standard sensors use a single global contrast threshold, leading to a trade-off between sensitivity and redundancy: low thresholds preserve static information but over-trigger under fast motion, while high thresholds reduce data volume but lose slow or static structures. We propose a multi-threshold event imaging model that assigns motion-compatible thresholds to different scene components, enabling faithful multi-velocity-scale imaging with fewer events. We also introduce a practical acquisition pipeline that implements this model on existing event cameras. Experiments on synthetic and real scenes validate the effectiveness of our approach in preserving both static structures and fast dynamics while reducing data volume.

In many interactive settings, from social and institutional environments to multi-agent systems, agents must infer latent behavioral structure from limited signals while their own actions shape the data they observe. This endogeneity violates the stationary, exogenous assumptions underlying standard likelihood-based methods, leading to failures in adaptation despite accurate clustering. We propose \emph{Epistemic Social Learning} (ESL), a two-timescale framework that couples belief-based inference with adaptive representation learning under endogenous interaction. At a fast timescale, agents maintain Bayesian beliefs over shared behavioral prototypes. At a slower timescale, prototypes are updated from belief-weighted interaction data via the recursion $\Theta_{m+1} = \Theta_m + \gamma_m \widehat{H}_m$, aligning learned representations with the interaction distributions induced by agent behavior. We formalize ESL as a stochastic approximation process with controlled Markov noise and show that its dynamics track the differential inclusion $\dot{\Theta} \in \mathcal{G}(\Theta)$, whose limit sets correspond to self-consistent interaction regimes. Across repeated games with behavioral shifts, ESL reduces post-switch regret by $26\%$ over strong baselines while improving decision-relevant prediction. These results reveal a fundamental gap between latent identification and adaptive performance under endogenous interaction.

Agentic large language models are increasingly used to solve real-world tasks by reasoning over goals, invoking tools, and interacting with external environments. Reinforcement learning provides a natural framework for improving these behaviors, and recent agent RL methods have achieved strong results across domains. However, the training dynamics of agent RL remain poorly understood, limiting our ability to diagnose instabilities and design more effective training algorithms. In this work, we identify a previously underexplored phenomenon in agent RL, which we term \emph{cyclical entropy eruption}. Unlike single-turn reasoning RL, where entropy typically collapses and stays low, agent RL training exhibits unique recurring cycles of sharp entropy eruption and gradual subsidence. We decompose this dynamic into three phases and provide theoretical and empirical analyses of each, explaining the mechanisms underlying its cyclical oscillation. We further show that degenerate patterns such as sentence duplication and hallucination, once acquired during eruption, can persist and accumulate across cycles. Motivated by these findings, we propose SEAL (Separation-Enhanced Agent Learning), a lightweight auxiliary loss that separates correct and incorrect trajectories in representation space, directly targeting the root cause of entropy eruption. Experiments across multiple benchmarks, models, and RL algorithms demonstrate that SEAL stabilizes training and yields stronger downstream agent performance.

LLM-based workflows compose specialized agents to execute complex tasks, and these agents usually share substantial context, allowing KV-Cache reuse to save computation. Existing approaches either manage KV-Cache at agent level and fail to exploit the reuse opportunities within workflows, or manage cache at the workflow level but assume that each workflow calls a static sequence of agents. However, practical workflows are typically dynamic, where the sequence of invoked agents and thus induced cache reuse opportunities depend on the context of each task. To serve such dynamic workflows efficiently, we build a system dubbed PBKV (\textbf{P}rediction-\textbf{B}ased \textbf{KV}-Cache Management). For each workflow, PBKV predicts the agent invocations in several future steps by fusing the guidance from historical workflows and context of the target workflow. Based on the predictions, PBKV estimates the reuse potential of cache entries and keeps the high-potential entries in GPU memory. To be robust to prediction errors, PBKV utilizes the predictions conservatively during both cache eviction and prefetching. Experiments on three workflow benchmarks show that PBKV achieves up to $1.85\times$ speedup over LRU on dynamic workflows, and up to $1.26\times$ speedup over the SOTA baseline KVFlow on the static workflow.

How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek's economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards. These simple economic signals induce decentralized credit assignment, driving planning without global orchestration or explicit communication protocols. The population evolves through economic selection: effective agents accumulate wealth and are mutated via exploitation, while ineffective ones go bankrupt and are replaced via exploration. We show that, initialized with weak agents, the economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks, including mathematical reasoning, financial research, scientific research, accelerator design, and distributed-system optimization. We further provide theoretical insights into how economic dynamics shape agent behaviors, linking local incentives to long-term global performance. Our results suggest a new path to multi-agent intelligence: rather than engineering coordination, we can design decentralized incentive structures under which it automatically emerges.

We argue that multi-agent test-time evolution is not single-agent evolution replicated N times. A single-agent learner can only evolve its own context and memory. A multi-agent system additionally evolves who collaborates, how they collaborate, and how knowledge flows across the population. These components have no single-agent counterpart and can produce phenomena such as emergent specialization. Yet prior test-time methods either confine experiences to individual agents, forfeiting cross-agent learning, or broadcast symmetrically to all agents, erasing the specialization that makes collaboration valuable. We present EVOCHAMBER, a training-free framework that instantiates test-time evolution at three levels over a coevolving agent pool. At its core is CODREAM (Collaborative Dreaming), a post-failure protocol in which agents collaboratively reflect, distill insights, and route them asymmetrically from strong agents to weak ones on the failed niche, preserving specialization while filling knowledge gaps. Team-level operators assemble niche-conditioned teams and select collaboration structures online. Population-level lifecycle operators fork, merge, prune, and seed agents under performance pressure. On three heterogeneous task streams with Qwen3-8B, EvoChamber reaches 63.9% on competition math, 75.7% on code, and 87.1% on multi-domain reasoning, outperforming the best baseline by 30% relative on math. These gains transfer to GPT-4.1-mini. Ablations attribute the largest single drop of -10.8% to removing CODREAM, confirming asymmetric cross-agent transfer as the primary driver. Starting from 20 identically initialized agents, four to five stable niche specialists spontaneously emerge, a structural signature of multi-agent evolution that no single-agent learner can express.

Hallucination remains a fundamental challenge in multimodal large language models (MLLMs), often stemming from unverified visual assumptions and reasoning processes that are weakly grounded in observable evidence. Existing approaches attempt to mitigate hallucination through self-reflection, multi-agent debate, or counterfactual verification. However, these methods remain largely opinion-driven: they lack explicit verification of the visual understanding process and may fail when multiple agents share the same incorrect perceptual assumptions, leading to consistent yet hallucinated conclusions. A promising direction is to augment MLLMs with external visual tools (e.g., OCR and grounding models) to acquire verifiable evidence. However, effective tool-augmented reasoning remains challenging due to two key failure modes: unreliable tool invocation, where models select inappropriate tools or produce incorrect parameters, and evidence--reasoning inconsistency, where models ignore or contradict the acquired evidence when forming final predictions. In this work, we propose EVA, an Evidence-seeking Visual Agent that reframes multimodal reasoning as an explicit process of evidence acquisition and verification. At the core of EVA is a unified evidence-grounded execution pipeline designed to address the above challenges through two tightly coupled mechanisms. First, we introduce \textit{Iterative Tool Replanning}, which dynamically refines tool selection and parameters based on intermediate observations, improving the reliability of tool usage. Second, we develop \textit{Evidence Consistency Verification}, an answer validation mechanism that improves alignment between the final prediction and the collected evidence, mitigating evidence--reasoning inconsistencies. In addition, to balance robustness and efficiency, EVA incorporates \textit{Selective Evidence Routing}, an adaptive fast--slow reasoning strategy that determines when external evidence is necessary. Visually straightforward queries are handled via direct reasoning, while complex or high-risk cases trigger tool-based evidence acquisition. By jointly addressing how to reliably acquire evidence and how to use it consistently, EVA transforms multimodal reasoning from passive answer validation into explicit evidence-backed decision making. Experimental results demonstrate that EVA achieves significantly improved reasoning reliability over direct VLM inference and multi-agent methods, while maintaining efficiency through selective tool invocation. These findings highlight structured and adaptive evidence utilization as a practical paradigm for hallucination-resistant multimodal reasoning.

Discharge summaries are crucial clinical documents for patient care, containing clinical context of a patient's overall admission, and are routinely reviewed by medical experts during patient readmission, ongoing care, and diagnostic decision-making. In practice, medical experts often must synthesize information across multiple lengthy discharge summaries by iteratively obtaining information from the documents, while also verifying the evidence supporting each answer. Although large language models (LLMs) are increasingly explored for clinical document question answering, existing benchmarks do not sufficiently capture this clinical setting: they either evaluate exam-style medical knowledge or focus on single-turn question answering with limited evidence-grounding evaluation. We introduce **EHRNote-ChatQA**, the first benchmark for evidence-grounded multi-turn clinical question answering over patients' multiple discharge summaries. Built from de-identified MIMIC-IV discharge summaries, EHRNote-ChatQA contains 967 patient-level multi-turn samples spanning one to five notes and 16,072 medical-expert-verified QA pairs (8,036 content questions, each paired with an evidence-grounding question) across eight clinical categories. We construct the benchmark through an expert-informed pipeline that combines a comprehensive discharge-summary structuring schema, expert-curated multi-turn QA templates, and LLM-based generation. Every single QA sample is then reviewed and revised by 11 medical experts over three weeks. Benchmarking 22 LLMs (both open and closed-sourced) reveals several findings; evidence grounding is consistently harder than content answering, multi-turn errors compound across turns, and strong performance on existing single-turn clinical QA benchmarks does not reliably transfer to this setting. These results establish EHRNote-ChatQA as a rigorous and practical benchmark for evaluating clinical QA systems.

The availability of open 12-lead electrocardiogram (ECG) datasets has significantly increased the number of studies focusing on automated ECG analysis. However, existing datasets often have limitations due to unverified annotations, overly processed data, or the absence of features such as fiducial points of the ECG. In this paper, we present a comprehensive collection of ECGs, with each record meticulously annotated by a team of seven cardiologists. Over 2,500 ECG records were annotated, with most records reviewed by at least four physicians. 1,527 ECG records of the dataset contain detailed annotations of PQRST segments, verified by two cardiologists. The dataset constitutes the largest collection of manually delineated ECG records to date, offering a valuable resource for researchers and practitioners in cardiology. This dataset, the first of its kind available for open use with multi-expert annotations, is suited for a variety of research tasks. It can be used for ECG abnormality classification, for analyzing patterns and annotation complexities across different heart abnormalities, and for tasks related to ECG delineation.

We propose Drift-Resistant Navigation World Model, a generative model that mitigates both perceptual drift and geometric drift in conventional rollout-based navigation world models. Existing methods recursively feed generated content into subsequent steps, causing noise accumulation and degraded predictions, i.e., perceptual drift. Meanwhile, their predictions often deviate from the agent’s motion, resulting in geometry drift. We address both types of drift by redesigning world-model prediction as an anchor-guided rollout. Instead of rolling out every frame sequentially, we first predict sparse future anchors that serve as stable long-range targets, and then generate intermediate frames within each chunk conditioned on both past context and future anchors. Importantly, these sparse anchors also provide geometric constraints, supported by bidirectional epipolar geometry, to localize where corresponding content should appear in the intermediate frames. Experiments on four benchmarks demonstrate consistent improvements over strong baselines in long-horizon visual quality, geometric consistency, and multi-view coherence. These gains further translate into improved downstream planning performance under the same planners, highlighting the importance of drift-resistant, geometry-aware prediction for reliable navigation world models.

Multi-agent LLM systems improve reasoning and tool use via role specialization, yet reinforcement learning (RL) post-training for such systems remains unstable and underexplored. We theoretically pinpoint a key source of instability when extending group-based RL to cooperative multi-agent LLM systems: under GRPO-style optimization, a global normalization baseline can mismatch heterogeneous agents' reward distributions, inducing gradient-norm instability. Based on this finding, we propose Dr. MAS, a simple and stable RL recipe for cooperative multi-agent LLM systems. Algorithmically, Dr. MAS normalizes advantages per agent using each agent's own reward statistics, which calibrates gradient scales and dramatically stabilizes the training. Systemically, Dr. MAS provides an end-to-end multi-agent RL framework with scalable orchestration, flexible per-agent LLM serving and optimization, and shared resource scheduling of actor backends. Unlike single-actor frameworks such as veRL, Dr. MAS natively supports multiple heterogeneous LLMs over a unified GPU pool. Lifecycle-aware backend management and dynamic dispatch release inactive models' GPU memory and schedule active agents on demand, enabling hardware-efficient co-training. We evaluate Dr. MAS on multi-agent math reasoning and multi-turn search with Qwen2.5 and Qwen3. Dr. MAS achieves clear gains over vanilla GRPO (e.g., +5.6\% avg@16 and +4.6\% pass@16 on math, and +15.2\% avg@16 and +13.1\% pass@16 on search) while largely eliminating gradient spikes. It also remains highly effective under heterogeneous agent-model assignments while improving efficiency. Code is available at https://anonymous.4open.science/r/DrMAS-0787.

Graph Foundation Models (GFMs) have attracted growing attention for their ability to model multi-domain graphs universally and generalize to unseen downstream tasks. However, existing GFMs typically rely on a single domain-invariant representation space, which inevitably blurs two fundamental connectivity patterns, \emph{homophily} and \emph{heterophily}, that govern how nodes relate across domains. Additionally, hard-partitioning the graph into disjoint subgraphs discards edges that are essential for self-supervised pre-training. In this work, we introduce $\underline{\text{HHGFM}}$, a $\underline{\text{H}}$omophilic and $\underline{\text{H}}$eterophilic Pattern-Disentangled $\underline{\text{G}}$raph $\underline{\text{F}}$oundation $\underline{\text{M}}$odel that encodes homophily and heterophily separately while keeping the original edge structure intact. Specifically, we propose a node-level soft disentanglement mechanism that estimates each neighbor's homophilic and heterophilic contributions and uses them as edge weights, thereby preserving the original graph structure. Low-pass and high-pass filters then serve as dual backbones to align homophilic and heterophilic patterns separately, supported by our generalization analysis. Extensive experiments on a range of graph datasets validate the effectiveness of our method.

Multi-Task Learning (MTL) is a fundamental problem in machine learning that has been extensively studied over the past decade. Recently, a variety of optimization-based MTL approaches have been proposed to jointly learn multiple tasks by modifying the optimization trajectory. In this paper, we argue that the design of mainstream optimization-based MTL methods implicitly assumes compatibility with momentum-free optimizers, which may limit the understanding of their effectiveness in modern training regimes. In practice, the instantaneously derived gradients from MTL operations contribute only marginally to the final parameter updates when momentum is present, resulting in an amortized rather than instant de-conflicting effect. Moreover, this amortized behavior can be further degraded under high-curvature optimization dynamics. To address this issue and enable the effective integration of mainstream MTL methods with advanced optimizers (e.g., Adam and Muon), we propose \texttt{APT} (Applicability of advanced oPTimizers), a lightweight framework featuring an adaptive momentum mechanism that balances the trade-off between instant and amortized de-conflicting. Furthermore, we show that the Muon optimizer can be interpreted as an implicit MTL learner, and we introduce a lightweight direction preservation strategy to better align with its orthogonalization process. Extensive experiments across four standard MTL benchmarks demonstrate that \texttt{APT} consistently enhances existing MTL approaches, yielding substantial performance gains.