ICML 2026 论文列表

As LLM-powered agents have been used for high-stakes decision-making, such as clinical diagnosis, it becomes critical to develop reliable verification of their decisions to facilitate trustworthy deployment. Yet, existing verifiers usually underperform owing to a lack of domain knowledge and limited calibration. To address this, we establish **GLEAN**, an agent verification framework with **G**uide**L**ine-grounded **E**vidence **A**ccumulatio**N** that compiles expert-curated protocols into trajectory-informed, well-calibrated correctness signals. GLEAN evaluates the step-wise alignment with domain guidelines and aggregates multi-guideline ratings into surrogate features, which are accumulated along the trajectory and calibrated into correctness probabilities using Bayesian logistic regression. Moreover, the estimated uncertainty triggers active verification, which selectively collects additional evidence for uncertain cases via expanding guideline coverage and performing differential checks. We empirically validate GLEAN with agentic clinical diagnosis across three diseases from the MIMIC-IV dataset, surpassing the best baseline by 12\% in AUROC and 50\% in Brier score reduction, which confirms the effectiveness in both discrimination and calibration. In addition, the expert study with clinicians recognizes GLEAN's utility in practice.

Autonomous agents for machine learning engineering have advanced rapidly, yet comparing their effectiveness remains difficult. Existing systems combine different techniques---multi-agent decomposition, iterative refinement, memory management, and planning---in varying configurations, making it unclear which components actually drive performance. Complicating evaluation, existing benchmarks rely on historical competitions whose data likely contaminates LLM training corpora and whose static baselines reflect outdated human performance. To address this, we conduct over 4,000 controlled experiments systematically ablating architectural components, alongside K-live, a new benchmark of 25 active competitions that provides a contamination-free, dynamic evaluation environment. Our findings challenge common design assumptions: iterative feedback contributes more than architectural complexity, and multi-agent coordination can hurt as often as it helps. These results provide concrete guidance for practitioners building ML engineering agents.

The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, necessitates maintaining rigorous logical integrity over extended horizons. However, prevalent memory preprocessing paradigms incur destructive de-contextualization. By compressing fluid sequential dependencies into pre-defined structures (e.g., embeddings or graphs), these methods sever the narrative integrity essential for deep reasoning. To address this, we propose E-mem, a framework shifting from Memory Preprocessing to Episodic Context Reconstruction inspired by biological engrams. E-mem employs a heterogeneous hierarchical architecture where multiple assistant agents maintain uncompressed memory contexts, while a central master agent orchestrates global planning. Unlike passive retrieval, our mechanism empowers assistants to locally reason within activated segments, extracting context-aware evidence before aggregation. Evaluations on the LoCoMo benchmark demonstrate that E-mem achieves over 54\% F1—surpassing the state-of-the-art GAM by 7.75\%—while reducing token cost by over 70\%. Our work is available on \url{https://anonymous.4open.science/r/E-mem-F6C3/}.

As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant security challenge. Existing detection methods typically rely on historical context. However, this retrospective logic struggles to identify deep malicious intents that are split across turns to hide future risks. Inspired by speculative decoding, we propose the Speculative Safety Honeypot (SSH) framework. SSH uses a multi-agent simulation system composed of small LLMs to build an action-level speculate-and-verify workflow. In the speculation stage, SSH predicts future behaviors of the target agent and asynchronously builds a trajectory tree to expose potential risks in advance. In the verification stage, the system uses the target agent's real actions to calibrate and prune the trajectory tree, effectively reducing false positives. As a plug-and-playable component, SSH provides existing detectors with rich decision redundancy beyond the current interaction slice. By judging risk based on the evolution of the entire trajectory tree rather than a single point in time, the system reduces the reliance on the absolute precision of individual detection components. This improves the defense resilience and the warning lead-time of agent systems against complex temporal attacks.

Logical reasoning encompasses deduction, induction, and abduction. However, while Large Language Models (LLMs) have effectively mastered the former two, abductive reasoning remains significantly underexplored. Existing frameworks, predominantly designed for static deductive tasks, fail to generalize to abductive reasoning due to unstructured state representation and lack of explicit state control. Consequently, they are inevitably prone to Evidence Fabrication, Context Drift, Failed Backtracking, and Early Stopping. To bridge this gap, we introduce Graph of States (GoS), a general-purpose neuro-symbolic framework tailored for abductive tasks. GoS grounds multi-agent collaboration in a structured belief states, utilizing a causal graph to explicitly encode logical dependencies and a state machine to govern the valid transitions of the reasoning process. By dynamically aligning the reasoning focus with these symbolic constraints, our approach transforms aimless, unconstrained exploration into a convergent, directed search. Extensive evaluations on two real-world datasets demonstrate that GoS significantly outperforms all baselines, providing a robust solution for complex abductive tasks. Code repo and all prompts: https://github.com/gaorch85/Graph-of-States.

Stock markets are one of the most complex systems in the modern world, where prices emerge from billions of decentralized interactions among heterogeneous participants in an ever-evolving information landscape. While high-fidelity simulation is important for understanding market dynamics, existing approaches face a persistent trade-off between structural and behavioral fidelity. To this end, we propose MarketSim, a large-scale stock market simulation framework with generative agents. MarketSim introduces a hierarchical multi-agent architecture that decouples strategic reasoning from high-frequency execution, enabling LLM agents to operate in a nanosecond-resolution, NASDAQ-like continuous double auction market. Building on this, we simulate over 15,000 heterogeneous market participants whose interactions shape and are shaped by an evolving market environment grounded in more than 12k real-world news articles, policy documents, and earnings reports. To evaluate our proposed MarketSim, we develop a comprehensive benchmark that includes stocks from 8 GICS sectors and 3 representative real-world scenarios, along with 5 stylized facts for market complexity and 5 price-related statistical metrics. Extensive experiments demonstrate that MarketSim not only captures key complexity properties of real-world markets, but also outperforms state-of-the-art baselines in tracking high-frequency price dynamics with an average MAPE of 3.48%, providing a scalable testbed for market analysis.

Fast Healthcare Interoperability Resources (FHIR) is the dominant standard for interoperable exchange of healthcare data. In FHIR, electronic health records form a directed graph of resources. Answering clinically meaningful questions over FHIR requires agents to perform multi-step reasoning, filtering, and aggregation across multiple resource types. Prior work shows that even tool-augmented LLM agents (retrieval, code execution, multi-turn planning) often select the wrong resources or violate traversal constraints. We study this problem in the context of FHIR-AgentBench, a benchmark for realistic question answering over real-world hospital data, and frame reasoning on FHIR as a sequential decision-making problem over a queryable structured graph. We implement a multi-turn CodeAct agent and post-train it with reinforcement learning using a custom harness and tools. A LLM Judge provides execution-grounded rewards. Compared to prompt-based, closed-model baselines, RL post-training improves performance while enforcing data-integrity constraints. Empirically, our approach improves answer correctness from 50% (o4-mini) to 77% on FHIR-AgentBench using a smaller and cheaper Qwen3-8B model. We present an end-to-end post-training pipeline (environment building, harness construction, model training and custom evaluation) that reliably improves multi-turn reasoning over structured clinical graphs.

In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)—where coordination with unknown partners is required—remains unexplored. To rigorously evaluate this, we introduce a large-scale benchmark **ICRL4AHT**, built upon a high-throughput JAX implementation of Overcooked-V2. Our benchmark includes a large, diverse teammate suite spanning both RL and heuristic policies, enabling controlled train-test shifts, and provides a reproducible end-to-end pipeline for teammate generation, learning-history collection, dataset construction, and online multi-episode evaluation. We evaluate representative history-conditioned ICRL algorithms, including Algorithm Distillation (AD) and Decision-Pretrained Transformer (DPT), across millions of transitions. Results reveal notable limitations: contrary to their success in single-agent domains, these baselines fail to exhibit robust test-time adaptation in multi-agent settings. Specifically, these methods frequently underperform random baselines across both unseen teammate and unseen layout tracks, with no clear in-context improvement over long horizons. These findings highlight the challenges of strategic inference under partial observability within the OvercookedV2 AHT protocol, establishing our benchmark as a critical testbed for next-generation coordination algorithms.

Large language models (LLMs) have enabled web agents that follow natural language goals through multi-step browser interactions. However, agents fine-tuned on specific trajectories and domain often struggle to generalize out of domain, and offline training can be compute-inefficient due to noisy, redundant trajectories and long accessibility-tree (AXTree) states. To address both issues, we propose Weasel, a trajectory selection method for offline training of web agents. Weasel selects a fixed-budget subset of trajectory steps by optimizing an objective that balances unary importance with pairwise diversity over states, websites, and interaction patterns, solving efficiently with a greedy algorithm. We further improve efficiency with target-centered AXTree pruning that keeps only content around the ground-truth action target, and we mitigate style mismatch for reasoning-native models by replacing expert traces with model-generated, style-consistent rationales. Across AgentTrek and NNetNav training datasets, evaluations in WebArena, WorkArena, and MiniWob, and experiments with Qwen2.5-7B, Gemma3-4B, and Qwen3-8B, Weasel improves out-of-domain performance while reducing training cost, producing roughly 9.7-12.5$\times$ training speedups over standard fine-tuning. We make the code available at https://github.com/fatemehpesaran310/weasel.

Formal specification is a powerful tool to guide the learning process and provides significant advantages over reward shaping: (1) mathematical rigor; (2) expressiveness to specify objectives and constraints, and (3) the ability to define tactics to achieve objectives. However, these benefits remain largely unexplored in the context of Multi-Agent Reinforcement Learning (MARL). This paper introduces HyPOLE, a novel framework for MARL under partial observability, where learning is guided by the expressive power of the so-called hyperproperties and, in particular, the temporal logic HyperLTL. We integrate Centralized Training for Decentralized Execution (CTDE) techniques with HyPOLE to synthesize decentralized policies, and our evaluation on SMAC, MessySMAC, and WildFire benchmark demonstrates clear advantages over baselines.

Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computational problem. We propose CocoRNA, a cooperative multi-agent reinforcement learning framework for RNA inverse design. CocoRNA simplifies the design task by decomposing it into smaller sub-problems, each solved collaboratively by multiple agents. This approach reduces the complexity of the problem and improves the exploration of design policies. During training, a centralized critic uses global structural information to guide the agents, enabling them to jointly optimize their design strategies. As a result, CocoRNA learns high-quality RNA design policies that generalize effectively to unseen structures without additional training. Experiments on the Rfam dataset demonstrate that CocoRNA substantially outperforms state-of-the-art methods in both success rate and design speed. Further experiments on other biological sequence design tasks highlight the effectiveness and broad potential of CocoRNA for complex design tasks.

Large Language Models have shown strong capabilities in complex problem solving, yet many agentic systems remain difficult to interpret and control due to opaque internal workflows. While some frameworks offer explicit architectures for collaboration, many deployed agentic systems operate as black boxes to users. We address this by introducing Agentic Workflow Reconstruction (AWR), a new task aiming to synthesize an explicit, interpretable stand-in workflow that approximates a black-box system using only input--output access. We propose AgentXRay, a search-based framework that formulates AWR as a combinatorial optimization problem over discrete agent roles and tool invocations in a chain-structured workflow space. Unlike model distillation, AgentXRay produces editable white-box workflows that match target outputs under an observable, output-based proxy metric, without accessing model parameters. To navigate the vast search space, AgentXRay employs Monte Carlo Tree Search enhanced by a scoring-based Red-Black Pruning mechanism, which dynamically integrates proxy quality with search depth. Experiments across diverse domains demonstrate that AgentXRay achieves higher proxy similarity and reduces token consumption compared to unpruned search, enabling deeper workflow exploration under fixed iteration budgets.

Large Language Model (LLM)-based scientific agents have accelerated scientific discovery, yet they often suffer from significant inefficiencies due to adherence to fixed initial priors. Existing approaches predominantly operate within a static hypothesis space, which restricts the discovery of novel phenomena, resulting in computational waste when baseline theories fail. To address this, we propose shifting the focus from searching hypotheses to evolving the underlying scientific principles. We present $\textbf{PiEvo}$, a principle-evolvable framework that treats scientific discovery as Bayesian optimization over an expanding principle space. By integrating Information-Directed Hypothesis Selection via Gaussian Process and an anomaly-driven augmentation mechanism, PiEvo enables agents to autonomously refine their theoretical worldview. Evaluation across four benchmarks demonstrates that PiEvo (1) achieves an average solution quality of up to 90.81\%$\sim$93.15\%, representing a 29.7\%$\sim$31.1\% improvement over the state-of-the-art, (2) attains an 83.3\% speedup in convergence step via significantly reduced sample complexity by optimizing the compact principle space, and (3) maintains robust performance across diverse scientific domains and LLM backbones. Code is publicly available at github.com/amair-lab/PiEvo.

Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVision-RL, a reinforcement learning framework for open-weight multimodal models that stabilizes training and sustains interaction. Our approach combines an oversampling–filtering–ranking rollout strategy with an accumulative tool reward to prevent collapse and encourage multi-turn tool use. Using a unified training pipeline, we develop PyVision-Image and PyVision-Video for image and video understanding. For video reasoning, PyVision-Video employs on-demand context construction, selectively sampling task-relevant frames during reasoning to significantly reduce visual token usage. Experiments show strong performance and improved efficiency, demonstrating that sustained interaction and on-demand visual processing are critical for scalable multimodal agents.

In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have emerged, adopting a localize–clip–answer pipeline in which the model actively identifies relevant video segments, performs dense sampling within those clips, and then produces answers. However, existing methods remain inefficient, suffer from weak localization, and adhere to rigid workflows. To solve these issues, we propose VideoTemp-o3, a unified agentic thinking-with-videos framework that jointly models video grounding and question answering. VideoTemp-o3 exhibits strong localization capability, supports on-demand clipping, and can refine inaccurate localizations. Specifically, in the supervised fine-tuning stage, we design a unified masking mechanism that encourages exploration while preventing noise. For reinforcement learning, we introduce dedicated rewards to mitigate reward hacking. Besides, from the data perspective, we develop an effective pipeline to construct high-quality long video grounded QA data, along with a corresponding benchmark for systematic evaluation across various video durations. Experimental results demonstrate that our method achieves remarkable performance on both long video understanding and grounding.

Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems improve GPU utilization at the cost of degraded inference performance, particularly time-to-first-token (TTFT). We attribute this degradation to the lack of awareness regarding future workload characteristics. In contrast, recent analyses have shown the strong periodicity and long-term predictability of real-world LLM serving workloads. In this paper, we propose \textit{one-for-many GPU prewarming}, which proactively loads parameters from multiple models onto GPUs based on workload forecasts. These prewarmed weights enable the system to promptly instantiate serving instances upon encountering request bursts. We design and implement WarmServe, a multi-LLM serving system incorporating three key techniques: (1) a model placement algorithm that optimizes prewarming decisions to minimize cross-model prewarming interference, (2) a KV cache reservation strategy that repurposes idle KV cache space on running GPUs for prewarming new models, and (3) an efficient GPU memory switching mechanism for tensor management. Evaluation on real-world datasets shows that WarmServe reduces tail TTFT by up to 50.8$\times$ compared to the state-of-the-art autoscaling-based system, while supporting up to 2.5$\times$ higher request throughput than the GPU-sharing system.

Foundation model-driven agents often struggle with long-horizon planning due to the transient nature of purely prompting-based reasoning. While existing skill induction methods mitigate this by distilling experience into state-blind parameterized scripts, they fail to capture the conditional logic required for robust execution in dynamic environments. In this paper, we propose Neuro-Symbolic Skill Induction (NSI), a framework that lifts interaction traces into modular, logic-grounded programs. By synthesizing explicit control flows and dynamic variable binding, NSI empowers agents to discover when and why to act. This paradigm enables the efficient generalization, allowing agents to induce skills from few-shot examples and flexibly adapt to unseen goals. Experiments on a series of agentic tasks demonstrate that NSI consistently outperforms state-of-the-art baselines, empowering agents to self-evolve into architects of logic-grounded skills. Project Page: https://sh-jj.github.io/NSI.

While existing multi-agent systems (MAS) can handle complex problems by enabling collaboration among multiple agents, they are often highly task-specific, relying on manually crafted agent roles and interaction prompts, which leads to increased architectural complexity and limited reusability across tasks. Moreover, most MAS communicate primarily through natural language, making them vulnerable to error accumulation and instability in long-context, multi-stage interactions within internal agent histories. In this work, we propose \textbf{Agent Primitives}, a set of reusable latent building blocks for LLM-based MAS. Inspired by neural network design, where complex models are built from reusable components, we observe that many existing MAS architectures can be decomposed into a small number of recurring internal computation patterns. Based on this observation, we instantiate three primitives (Review, Voting and Selection, and Planning and Execution), all communicating via key–value (KV) cache to mitigate information degradation across multi-stage interactions. To enable automatic system construction, an Organizer agent automatically selects and composes primitives for each query, guided by a lightweight knowledge pool of previously successful configurations, forming a primitive-based MAS. Experiments show that primitives-based MAS improve average accuracy by 12.0–16.5\% over single-agent baselines, reduce token usage and inference latency by approximately 3$\times$–4$\times$ compared to text-based MAS, while incurring only 1.3$\times$–1.6$\times$ overhead relative to single-agent inference and providing more stable performance across model backbones.

We consider anonymous multi-agent path finding (MAPF) where a set of robots is tasked to travel to a set of targets on a finite, connected graph. We show that MAPF can be cast as a special class of multi-marginal optimal transport (MMOT) problems with an underlying Markovian structure, under which the exponentially large MMOT collapses to a linear program (LP) polynomial in size. Focusing on the anonymous setting, we establish conditions under which the corresponding LP is feasible, totally unimodular, and yields min-cost, integral~$(\{0,1\})$ transports that do not overlap in both space and time. To adapt the approach to large-scale problems, we cast the MAPF-MMOT in a probabilistic framework via Schrödinger bridges. Under standard assumptions, we show that the Schrödinger bridge formulation reduces to an entropic regularization of the corresponding MMOT that admits an iterative Sinkhorn-type solution. The Schrödinger bridge, being a probabilistic framework, provides a shadow (fractional) transport that we use as a template to solve a reduced LP and demonstrate that it results in near-optimal, integral transports at a significant reduction in complexity. Extensive experiments highlight the optimality and scalability of the proposed approaches.