ICLR 2026 论文列表

While Large Language Models (LLMs) have shown remarkable advancements in reasoning and tool use, they often fail to generate optimal, grounded solutions under complex constraints. Real-world travel planning exemplifies these challenges, evaluating agents’ abilities to handle constraints that are explicit, implicit, and even evolving based on interactions with dynamic environments and user needs. In this paper, we present ATLAS, a general multi-agent framework designed to effectively handle such complex nature of constraints awareness in real-world travel planning tasks. ATLAS introduces a principled approach to address the fundamental challenges of constraint-aware planning through dedicated mechanisms for dynamic constraint management, iterative plan critique, and adaptive interleaved search. ATLAS demonstrates state-of-the-art performance on the TravelPlanner benchmark, improving the final pass rate from 23.3% to 44.4% over its best alternative. More importantly, our work is the first to demonstrate quantitative effectiveness on real-world travel planning tasks with live information search and multi-turn feedback. In this realistic setting, ATLAS showcases its superior overall planning performance, achieving an 84% final pass rate which significantly outperforms baselines including ReAct (59%) and a monolithic agent (27%).

Maintaining role-awareness in Role-Playing Conversational Agents (RPCAs) is a significant challenging, largely because the creative nature of role-playing makes it difficult to design verifiable reward signals for reinforcement learning (RL). To address this, we propose VeriRole, a new framework designed to enhance the role-awareness of agents through a structured, verifiable reasoning process. The core of our framework is a 'hint' mechanism, designed to first extract deterministic cues from the context, before the main response generation.Building on these hints, we introduce a Verifiable Role-Awareness Reward (VRAR) to provide a verifiable signal for role-awareness. Experimental results demonstrate the effectiveness of our approach. Our Qwen2.5-32B model, optimized with VeriRole, achieves an 18.9% and 4.55% increase in average scores on the RAIDEN and CharacterEval benchmarks, respectively. These results confirm that VeriRole can effectively quantify and improve role-awareness, leading to superior persona consistency and robustness. To ensure reproducibility, all prompts are detailed in the Appendix, and the associated training data has been made publicly available.

The utility of Role-Playing Language Agents in sociological research is growing alongside the adoption of Large Language Models. For realism in social simulation, these agents must adhere to their personas defined by character profiles, yet existing strategies—static prompt engineering or costly fine-tuning—fail to adapt personas to dynamic scenarios. Psychological theories, such as the Cognitive-Affective Personality Systems, provide a crucial explanation for this failure: a persona's influence on behavior is not static but varies with the scenarios. This context-dependence highlights the critical need for adaptive persona management. To address this gap, we propose a novel, theory-driven method that dynamically estimates context-dependent persona importance and integrates it into weighted reward-guided decoding, enabling inference-time persona following. Specifically, we introduce Persona Dynamic Decoding (PDD) framework that consists of two key components: (1) Persona Importance Estimation (PIE) module, which dynamically quantifies the contextual importance of persona attributes without requiring ground-truth supervision; and (2) Persona-Guided Inference-Time Alignment (PIA) paradigm, which leverages these importance scores to construct weighted multi-objective rewards and modulate generation probabilities during inference. Extensive experiments show the effectiveness of our method in utterance consistency and behavioral fidelity.

Alpha mining seeks to identify predictive alpha factors that generate excess returns beyond the market from a vast and noisy search space; however, existing approaches struggle to facilitate the systematic evolution of alphas. Traditional methods, such as genetic programming, are unable to interpret human natural-language instructions and often fail to extract valuable insights from unsuccessful attempts, leading to low interpretability and inefficient exploration. Analogously, without mechanisms for systematic evolution, e.g., long-term planning and reflection, multi-agent approaches may easily fall into repetitive evolutionary routines, thereby failing to realize efficient self-evolution. To overcome these limitations, we introduce **AlphaAgentEvo**, a self-evolving Agentic Reinforcement Learning (ARL) framework for alpha mining, which moves alpha mining beyond the brittle “search–backtest–restart” cycle toward a continuous trajectory of evolution. Instructed by a hierarchical reward function, our agent engages in self-exploration of the search space, progressively learning basic requirements (e.g., valid tool calls) and then harder objectives (e.g., continuous performance improvements). Through this process, the agent acquires advanced behaviors such as long-horizon planning and reflective reasoning, which enable it to actively react to the underlying state (e.g., market regime shifting) and realize a self-evolving agent, taking a step toward more principled and scalable alpha mining. Extensive experiments demonstrate that AlphaAgentEvo achieves more efficient alpha evolution and generates more diverse and transferable alphas, consistently surpassing a wide range of baselines. Notably, with only 4B parameters, it outperforms LLM-driven evolution methods configured with state-of-the-art close-source reasoning models, highlighting the promise of ARL for next-generation alpha mining.

We introduce ShinkaEvolve: a new framework leveraging large language models (LLMs) to advance scientific discovery with state-of-the-art performance and efficiency. The field of LLM-driven scientific discovery has seen significant progress, but has yet to overcome a critical limitation: sample inefficiency, requiring thousands of samples to identify effective solutions. ShinkaEvolve takes a concrete step towards addressing this critical limitation by introducing three key innovations: a parent sampling technique balancing exploration and exploitation, code novelty rejection-sampling for efficient search space exploration, and a bandit-based LLM ensemble selection strategy. When applied to the canonical circle-packing optimization task, ShinkaEvolve discovers a new state-of-the-art circle packing solution using only 150 samples, orders of magnitude fewer than prior frameworks. Furthermore, applied to a broader set of engineering problems, ShinkaEvolve designs robust agentic harnesses for AIME mathematical reasoning tasks, identifies improvements to ALE-Bench competitive programming solutions, and discovers novel mixture-of-expert load balancing loss functions to stabilize LLM training itself. We provide ShinkaEvolve's full code together with this submission, which will be open-sourced to accelerate open advancements to open-ended automated discovery across diverse computational problems.

Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks. While augmenting these agents with planners can improve task decomposition, they remain constrained by the inherent limitations of performing all actions through GUI manipulation, leading to brittleness and inefficiency. In this work, we introduce a more robust and flexible paradigm: enabling agents to use coding as an enhanced action. We present CoAct-1, a novel multi-agent system that synergistically combines GUI-based control with direct programmatic execution. CoAct-1 features an Orchestrator that dynamically delegates subtasks to either a conventional GUI Operator or a specialized Programmer agent, which can write and execute Python or Bash scripts. This hybrid approach allows the agent to bypass inefficient GUI action sequences for tasks like file management and data processing, while still utilizing visual interaction when necessary. We evaluate our system on the challenging OSWorld and WindowsAgentArena benchmark, where CoAct-1 achieves a new state-of-the-art success rate of 60.8% on OSWorld and 52.5% on WindowsAgentArena, significantly outperforming prior methods. Furthermore, our approach dramatically improves efficiency, reducing the average number of steps required to complete a task to just 10.15 on OSWorld, compared to 15 for leading GUI agents. Our results demonstrate that integrating coding as a core action provides a more powerful, efficient, and scalable path toward generalized computer automation.

Large Language Model (LLM)-based agentic systems, often comprising multiple models, complex tool invocations, and orchestration protocols, substantially outperform monolithic agents. Yet this very sophistication amplifies their fragility, making them more prone to system failure. Pinpointing the specific agent or step responsible for an error within long execution traces defines the task of \textbf{agentic system failure attribution}. Current state-of-the-art reasoning LLMs, however, remain strikingly inadequate for this challenge, with accuracy generally below $10\\%$. To address this gap, we propose AgenTracer, the first automated framework for annotating failed multi-agent trajectories via counterfactual replay and programmed fault injection, producing the curated dataset TracerTraj. Leveraging this resource, we develop AgenTracer-8B, a lightweight failure tracer trained with multi-granular reinforcement learning, capable of efficiently diagnosing errors in verbose multi-agent interactions. On {Who\&When} benchmark, AgenTracer-8B outperforms giant proprietary LLMs like Gemini-2.5-Pro and Claude-4-Sonnet by up $18.18\\%$, setting a new standard in LLM agentic failure attribution. More importantly, AgenTracer-8B delivers actionable feedback to off-the-shelf multi-agent systems like MetaGPT and MaAS with $4.8\sim14.2\\%$ performance gains, empowering self-correcting and self-evolving agentic AI.

While Vision–language models (VLMs) have demonstrated remarkable performance across multi-modal tasks, their choice of vision encoders presents a fundamental weakness: their low-level features lack the robust structural and spatial information essential for document understanding and web agents. To bridge this gap, we introduce DAVE, a vision encoder purpose-built for VLMs and tailored for these tasks. Our training pipeline is designed to leverage abundant unlabeled data to bypass the need for costly large-scale annotations for document and web images. We begin with a self-supervised pretraining stage on unlabeled images, followed by a supervised autoregressive pretraining stage, where the model learns tasks like parsing and localization from limited, high-quality data. Within the supervised stage, we adopt two strategies to improve our encoder’s alignment with both general visual knowledge and diverse document and web agentic tasks: (i) We introduce a novel model-merging scheme, combining encoders trained with different text decoders to ensure broad compatibility with different web agentic architectures. (ii) We use ensemble training to fuse features from pretrained generalist encoders (e.g., SigLIP2) with our own document and web-specific representations. Extensive experiments on classic document tasks, VQAs, web localization, and agent-based benchmarks validate the effectiveness of our approach, establishing DAVE as a strong vision encoder for document and web applications.

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates security modeling, while the integration of traditional software with AI components entangles novel LLM vulnerabilities with conventional security risks. Existing frameworks only partially address these challenges as they either capture specific vulnerabilities only or require modeling of complete agents. To address these limitations, we introduce threat snapshots: a framework that isolates specific states in an agent's execution flow where LLM vulnerabilities manifest, enabling the systematic identification and categorization of security risks that propagate from the LLM to the agent level. We apply this framework to construct the $b^3$ benchmark, a security benchmark based on 194,331 unique crowdsourced adversarial attacks. We then evaluate 34 popular LLMs with it, revealing, among other insights, that enhanced reasoning capabilities improve security, while model size does not correlate with security. We release our benchmark, dataset, and evaluation code to facilitate widespread adoption by LLM providers and practitioners, offering guidance for agent developers and incentivizing model developers to prioritize backbone security improvements.

Ensembling Large Language Models (LLMs) has gained attention as a promising approach to surpass the performance of individual models by leveraging their complementary strengths. In particular, aggregating models’ next-token probability distributions to select the next token has been shown to be effective in various tasks. However, while successful for short-form answers, its application to long-form generation remains underexplored. In this paper, we show that using existing ensemble methods in long-form generation requires a careful choice of ensembling positions, since the standard practice of ensembling at every token often degrades performance. We identify two key factors for determining the ensembling positions: tokenization mismatch across models and consensus in their next-token probability distributions. Based on this, we propose $\textbf{SAFE}$, ($\textbf{S}$table $\textbf{A}$nd $\textbf{F}$ast LLM $\textbf{E}$nsembling), a framework that selectively ensembles by jointly considering these factors. To further improve stability, we apply a probability sharpening strategy when the ensemble distribution becomes overly smooth, enabling the selection of more confident tokens during ensembling. Our experiments on diverse benchmarks, including MATH500 and BBH, demonstrate that SAFE outperforms existing methods in both accuracy and efficiency, with gains achieved even when ensembling fewer than 1\% of tokens.

Recent advances in large language models (LLMs) have enabled agents that automate scientific discovery by interpreting data, generating analysis pipelines, and executing them with computational tools. However, existing benchmarks remain largely limited to unimodal datasets and slice-level tasks, overlooking the fact that real discovery requires multimodal integration, modeling, and hypothesis-driven reasoning. To address this gap, we introduce MoSciBench, the first benchmark for multimodal scientific discovery, constructed from peer-reviewed studies through a principled four-stage pipeline. MoSciBench spans six scientific domains, seven data modalities, and five categories of discovery questions, yielding 88 individual, end-to-end, data-driven tasks. Each task is designed as a cross-modal hypothesis verification workflow, requiring agents to align and integrate heterogeneous datasets before modeling and reasoning. We further evaluate four representative agent frameworks across multiple LLM families. Results show that multimodal discovery is substantially harder than unimodal tasks: even the strongest agents achieve only 48.94\% accuracy, with over 60\% of failures due to cross-modal alignment. Lightweight workflow scaffolding consistently improves performance, reducing alignment errors by 5–10\% and raising accuracy by 5.7\% on average. Our benchmark and evaluation framework thus establish a rigorous testbed for advancing LLM agents toward realistic, multimodal scientific discovery.

Multi-agent reinforcement learning (MARL) confronts a fundamental tension between stability and expressiveness. Stability requires avoiding divergence under non-stationary updates, while expressiveness demands capturing multimodal strategies for heterogeneous coordination. Existing methods sacrifice one for the other: value-decomposition and trust-region approaches ensure stability but assume restrictive unimodal policies, while expressive generative models lack optimization guarantees. To address this challenge, we introduce **H**eterogeneous **A**gent **Q**-weighted Policy **O**ptimization (**HAQO**), a framework unifying sequential advantage-aware updates, Q-weighted variational surrogates, and entropy regularization. Our analysis establishes monotone improvement guarantees under bounded critic bias, extending trust-region theory to diffusion-based policies with intractable log-likelihoods. HAQO achieves superior returns and reduced variance compared to policy-gradient baselines across diverse benchmarks. The ablation studies confirm sequential updates ensure stability, expressive policies enable multimodality, and entropy regularization prevents collapse. HAQO reconciles stability and expressiveness in MARL with theoretical rigor and practical effectiveness.

The multi-commodity flow (MCF) problem is a fundamental topic in network flow and combinatorial optimization, with broad applications in transportation, communication, and logistics, etc. Nowadays, the rapid expansion of allocation systems has posed challenges for existing optimization engines in balancing optimality and tractability. In this paper, we present Pram, the first ML-based method that leverages the reasoning power of multimodal language models (MLMs) for addressing the trade-off dilemma—a great need of service providers. As part of our proposal, Pram (i) quickly computes high-quality allocations by dividing the original problem into local subproblems, which are then resolved by an MLM-powered "agent", and (ii) ensures global consistency by harmonizing these subproblems via a multi-agent reinforcement learning algorithm. Theoretically, we show that Pram, which learns to perform gradient descent in context, provably converges to the optimum within the family of MCF problems. Empirically, on real-world datasets and public topologies, Pram achieves performance comparable to, and in some cases even surpassing, linear programming solvers (very close to the optimal solution), and substantially lower runtimes (one to two orders of magnitude faster). Moreover, Pram exhibits strong robustness (<10\% performance degradation under failures or bursts), demonstrating MLM's generalization ability to unforeseen events. Pram is objective-agnostic and seamlessly integrates with mainstream allocation systems, providing a practical and scalable solution for future networks.

The challenge of coalition formation games lies in efficiently navigating the exponentially large space of possible coalitions to identify the optimal partition. While existing approaches to solve coalition formation games either provide optimal solutions with limited scalability or approximate solutions without quality guarantees, we propose a novel scalable and sample-efficient approximation method based on deep reinforcement learning. Specifically, we model the coalition formation problem as a finite Markov decision process and use deep neural network to approximate optimal coalition structures within the full and abstracted coalition space. Moreover, our method is applicable to bi-level optimization problems in which coalition values are determined by the policies of individual agents at a lower decision-making level. This way, our approach facilitates dynamic, adaptive adjustments to coalition value assessments as they evolve over time. Empirical results demonstrate our algorithm's effectiveness in approximating optimal coalition structures in both normal-form and sequential mixed-motive games.

The increasing autonomy of Large Language Models (LLMs) necessitates a rigorous evaluation of their potential to aid in cyber offense. Existing benchmarks often lack real-world complexity and are thus unable to accurately assess LLMs' cybersecurity capabilities. To address this gap, we introduce PACEbench, a practical AI cyber-exploitation benchmark built on the principles of realistic vulnerability difficulty, environmental complexity, and cyber defenses. Specifically, PACEbench comprises four scenarios spanning single, blended, chained, and defense vulnerability exploitations. To handle these complex challenges, we propose PACEagent, a novel agent that emulates human penetration testers by supporting multi-phase reconnaissance, analysis, and exploitation. Extensive experiments with seven frontier LLMs demonstrate that current models struggle with complex cyber scenarios, and none can bypass defenses. These findings suggest that current models do not yet pose a generalized cyber offense threat. Nonetheless, our work provides a robust benchmark to guide the trustworthy development of future models.

Dual Modular Redundancy (DMR) is a highly effective mechanism for detecting silent data corruption (SDC)—a critical reliability concern in large language model (LLM) training—by executing each operation twice. However, its high computation overhead has prevented practical deployment at scale. In this paper, we present SpareTrain, an LLM training system that achieves complete DMR with minimal overhead by repurposing the activation checkpointing mechanism and exploiting idle GPU time. Evaluations on up to 32 H200 GPUs show that SpareTrain improves throughput by 12–35\% over naive DMR, corresponding to only 3–14\% overhead compared to unprotected training, while maintaining full DMR error detection capabilities.

Despite improvements by length extrapolation, efficient attention and memory modules, handling infinitely long documents without performance degradation during extrapolation remains the ultimate challenge in long-text processing. To solve this problem, We introduce a novel agent workflow, \method, which processes text in segments and updates memory through an overwrite strategy, addressing the challenge of long-context task through enhanced memory management. We further extend the DAPO algorithm to directly optimize memory ability in an end-to-end fashion, facilitating training via independent-context multi-conversation generation. Experimental results demonstrate that MemAgent has superb long-context capabilities, being able to extrapolate from an 8K context to a 3.5M QA task with a performance loss of less than 10\% and achieving over 95\% on the 512K NIAH test.

Recent advances demonstrate that multimodal large language models (MLLMs) exhibit strong multimodal in-context learning (ICL) capabilities, enabling them to adapt to novel vision-language tasks from a few contextual examples. However, existing ICL approaches face challenges in reconciling generalization with robustness across diverse tasks and noisy contextual examples: manually selecting examples produces clean contexts but is labor-intensive and task-specific, while similarity-based retrieval improves scalability but could introduce irrelevant or structurally inconsistent samples that degrade ICL performance. To address these limitations, we propose ContextNav, the first agentic framework that integrates the scalability of automated retrieval with the quality and adaptiveness of human-like curation, enabling noise-robust and dynamically optimized contextualization for multimodal ICL. ContextNav unifies context management and noise-robust contextualization within a closed-loop workflow driven by graph-based tool orchestration. Specifically, it builds a resource-aware multimodal embedding pipeline, maintains a retrievable vector database, and applies agentic retrieval and structural alignment to construct noise-resilient contexts. An Operational Grammar Graph (OGG) further supports adaptive toolchain planning and optimization, enabling the agent to refine its strategies based on downstream feedback. Experimental results demonstrate that ContextNav achieves state-of-the-art performance across various datasets, underscoring the promise of agentic workflows for advancing scalable and robust contextualization in multimodal ICL. The code will be made publicly available on GitHub.

With the rapid development of large language models (LLMs), identifying efficient strategies for training such large-scale systems has become increasingly critical. Although LLMs have achieved remarkable success across diverse applications, the necessity of maintaining full dense matrices during pre-training has been questioned, giving rise to parameter-efficient sparse pre-training methods which retains parameter-efficiency in both training and inference. These methods can be further divided into connectivity sparse training and spectral sparse training, with dynamic connectivity sparse training and low-rank factorization emerging as representative approaches for the two branches. However, a unified framework that effectively combines the strengths of both has yet to be established. In this work, we observe that the cancellation effect between the sparse and low-rank branches may limit the expressivity of the model, manifesting as output conflicts when the two components are combined. To address this issue, we propose a novel scheme that integrates dynamic sparse training with low-rank training, introducing a simple yet effective $\textbf{alignment loss}$ to mitigate the disagreement between the two branches and promote better collaboration. We validate this scheme by combining a representative dynamic sparse training method, CHTs, with low-rank training, resulting in a new parameter-efficient training approach termed $\textbf{CHTsL}$. The method is evaluated on LLaMA60M and LLaMA130M using the OpenWebText and C4 datasets, where only 10\%, 20\%, and 30\% of the parameters are preserved compared to dense training. Experimental results demonstrate that our proposed scheme effectively alleviates the cancellation effect and improves training stability and performance compared to the naive combination of sparse and low-rank components. Also, the new scheme enables CHTsL to consistently outperform other parameter-efficient sparse training methods under the same parameter budget, achieving performance most close to dense training.