ICML 2026 Papers

Cross-architecture migration of high-performance libraries dictates ecosystem readiness on emerging hardware. The challenge is twofold: disentangling library-scale dependencies and performance-critical kernels with ISA-specific SIMD intrinsics, often trading migration speed for peak performance. While LLM-based agents offer a promising approach, are confined to function-level tasks or scalar code, failing to assess agents’ capabilities and limitations in realistic, library-scale migration. We present QM-LibBench, a benchmark for cross-architecture library-scale code migration, featuring 85 critical kernels from widely used libraries, including OpenCV, libjpeg, and NCNN. It supports comprehensive evaluations of compilability, correctness, and performance across major transitions: ARM→RISC-V, x86→ARM, and ARM→LoongArch. Evaluation of 12 SOTA agent-LLM combinations on QM-LibBench reveals that, due to the lack of library-level navigation and hardware-aware optimization, agents regress to superficial pattern matching, yielding only 20.88\% correctness and 0.83 speedup for libjpeg. Motivated by these findings, we further propose FSCM, a multi-agent framework incorporating hardware-aware global reconfiguration and performance optimization. FSCM improves OpenCV correctness to 71\%. The benchmark and code are available at https://github.com/WisdomJoy/QM-LibBench.

Cooperation is central to multi-agent reinforcement learning (MARL), yet learned coordination can be fragile when external perturbations disrupt inter-agent interactions. Prior robust MARL methods have primarily considered value-oriented attacks, leaving a gap in robustness when interaction structures themselves are corrupted. In this paper, we propose an interaction-breaking adversarial learning (IBAL) framework that takes an information-theoretic view to construct attacks that impede coordination by perturbing agents’ observations and actions, and trains agents to perform reliably under such disruptions. Empirically, our approach improves robustness over existing robust MARL baselines across diverse attack settings and yields stronger performance even under agent-missing scenarios. Our code is available at https://sunwoolee0504.github.io/IBAL.

Large Language Model (LLM) agents use memory to learn from past interactions. However, this reliance on memory introduces a critical security risk: an adversary can inject seemingly harmless records into an agent's memory to manipulate its future behavior. This vulnerability is characterized by two core aspects: First, the malicious effect of injected records is only activated within a specific context, making them hard to detect when individual memory entries are audited in isolation. Second, once triggered, the manipulation can initiate a self-reinforcing error cycle: the corrupted outcome is stored as precedent, which not only amplifies the initial error but also progressively lowers the threshold for similar attacks in the future. To address these challenges, we introduce \emph{A-MemGuard} (\underline{A}gent-\underline{Mem}ory \underline{Guard}), the first defense framework for LLM agent memory. The core idea of our work is the insight that memory itself must become both \emph{self-checking} and \emph{self-correcting}. Without modifying the agent's core architecture, A-MemGuard combines two mechanisms: (1) \textbf{consensus-based validation}, which detects anomalies by comparing reasoning paths derived from multiple related memories and (2) a \textbf{dual-memory structure}, where detected failures are distilled into ``lessons'' stored separately and consulted before future actions, breaking error cycles and enabling adaptation. Comprehensive evaluations on multiple benchmarks show that A-MemGuard effectively cuts attack success rates by over 95\% while incurring a minimal utility cost. This work shifts LLM memory security from static filtering to a proactive, experience-driven model where defenses strengthen over time.

We present SWE-Bench Pro, a comprehensive benchmark designed to evaluate software engineering capabilities through complex, realistic programming challenges. This benchmark extends beyond traditional algorithmic problems to encompass the full spectrum of professional software development tasks. The dataset comprises 1,865 problems sourced from 41 active software engineering repositories, spanning 123 unique programming languages and various application domains. The benchmark is structured into public and private components, with public access to problems from 11 repositories and private evaluation sets from 12 repositories across 4 distinct problem categories. SWE-Bench Pro addresses limitations of existing evaluation frameworks by incorporating problems that reflect real-world software engineering scenarios, including substantial codebases, complex enterprise applications, and multi-file projects requiring sophisticated reasoning and code modification skills. Problems range from early-stage startup environments to enterprise-level applications, with the private commercial set remaining inaccessible to maintain evaluation integrity while enabling public access to representative problems for professional development. Our evaluation methodology employs diverse coding approaches and models under controlled conditions, ensuring robust performance assessment across multiple programming paradigms. Results demonstrate significant performance variations across different problem categories, with traditional algorithmic challenges showing notably higher success rates compared to complex, multi-file engineering tasks. The benchmark reveals substantial gaps in current capabilities for handling real-world software engineering scenarios, particularly in areas requiring deep contextual understanding, cross-file reasoning, and integration with existing large-scale systems. This work contributes a more comprehensive and realistic evaluation framework for assessing software engineering capabilities, providing insights into current limitations and establishing a foundation for future development in automated software engineering tools and methodologies.

Self-attention dominates the computational and memory cost of long-context LLM inference across both prefill and decode phases. To address this challenge, we introduce **Sketch\&Walk** Attention, a training-free sparse attention method that determines sparsity with lightweight sketches and deterministic walk. Sketch\&Walk applies Hadamard sketching to get inexpensive approximations of attention scores, then aggregates these estimates across layers via a walk mechanism that captures attention influence beyond direct interactions between tokens. The accumulated walk scores are used to select top-$k$ attention blocks, enabling dynamic sparsity with a single training-free algorithm that applies uniformly to both the prefill and decode phases, together with custom sparse attention kernels. Across a wide range of models and tasks, Sketch\&Walk maintains near-lossless accuracy at 20\% attention density and can slightly outperform dense attention in some settings, while achieving up to $4.7\times$ end-to-end attention speedup over FlashAttention-2.

To improve generalization and resilience in human–robot collaboration (HRC), robots must contend with diverse combinations of human behaviors and contexts, motivating multi-agent reinforcement learning (MARL). However, inherent heterogeneity between robots and humans creates a rationality gap (RG), where decentralized policy updates deviate from cooperative joint optimization. The resulting learning problem is a general-sum differentiable game, so independent policy-gradient updates can oscillate or diverge without added structure. We propose heterogeneous-agent Lyapunov policy optimization (HALO), a framework that stabilizes decentralized MARL by enforcing Lyapunov-based contraction in policy-parameter space. Unlike Lyapunov-based safe RL, which targets state/trajectory constraints in constrained Markov decision processes, HALO uses Lyapunov certification to stabilize decentralized policy learning. HALO rectifies decentralized gradients via optimal quadratic projections, ensuring monotonic contraction of RG and enabling effective exploration of open-ended interaction spaces. Extensive simulations and real-world humanoid-robot experiments show that this certified stability improves generalization and robustness in collaborative corner cases.

Large language models are increasingly evaluated as interactive agents, yet standard agent benchmarks conflate two qualitatively distinct sources of success: semantic tool-use and interface-specific interaction pattern memorization. Because both mechanisms can yield identical task success on the original interface, benchmark scores alone are not identifiable evidence of environment-invariant capability. We propose **PIPE**, a protocol-level evaluation augmentation for diagnosing interface reliance by minimally rewriting environment interfaces while preserving task semantics and execution behavior. Across 16 environments from AgentBench and AgentGym and a range of open-source and API-based agents, PIPE reveals that task-specific trajectory-SFT can amplify reliance on training-time interface forms: in several environments, agents with trajectory-SFT degrade sharply under minimal interface rewrites, whereas other agents are often more stable. We further introduce Interface Reliance (IR), a counterbalanced alias-based metric that quantifies preference for training-time interfaces, and show that interface shortcutting exhibits environment-dependent, non-monotonic training dynamics that remain invisible under standard evaluation. Our code is available at https://github.com/ChengZe2005/What-Do-Agents-Learn-from-Trajectory-SFT-Semantics-or-Interfaces-.

We introduce **Native Parallel Reasoner (NPR)**, a teacher-free framework that enables Large Language Models (LLMs) to self-evolve genuine parallel reasoning capabilities. NPR transforms the model from sequential emulation to native parallel cognition through three key innovations: (1) a **self-distilled** progressive training paradigm that transitions from cold-start format discovery to strict topological constraints without external supervision; (2) a novel **Parallel-Aware Policy Optimization (PAPO)** algorithm that optimizes branching policies directly within the execution graph, allowing the model to learn adaptive decomposition via trial and error; and (3) a robust **NPR Engine** that refactors memory management and flow control of SGLang to enable stable, large-scale parallel RL training. Across eight reasoning benchmarks, NPR trained on Qwen3-4B achieves performance gains of up to 24.5\% and inference speedups up to 4.6$\times$. Unlike prior baselines that often fall back to autoregressive decoding, NPR demonstrates 100\% genuine parallel execution, establishing a new standard for self-evolving, efficient, and scalable agentic reasoning.

Large language models (LLMs) have shown promising potential in materials science, enabling tasks ranging from knowledge retrieval to property prediction. Existing materials science benchmarks mainly focus on perceptual or knowledge-based tasks, largely ignoring the structure modelling tasks, a core challenge in real scientific workflows. In practice, constructing and manipulating atomic structures is one of the most creative and least automated steps in materials research. In this work, we introduce AtomWorld, a benchmark designed to evaluate the abilities of LLMs on structure modifications. The benchmark includes ten fundamental actions under four widely used modelling categories, enabling verifiable evaluation metrics. We find that Gemini 2.5 Pro generally performs the best. While the success rate decreases markedly with increasing modelling complexity, with particularly low success rates (below 12\% for rotation) for operations involving complex spatial relations. Our results suggest that contemporary LLMs are better suited as copilots for materials structure modelling rather than fully unsupervised autonomous scientific agents. Beyond evaluation, AtomWorld also serves as a testbed and playground for developing future structure-aware models, including reinforcement learning and agentic approaches.

As LLM-based agents increasingly operate in high-stakes domains with real-world consequences, ensuring their behavioral safety becomes paramount. The dominant oversight paradigm, *LLM-as-a-Judge*, faces a fundamental dilemma: how can probabilistic systems reliably supervise other probabilistic systems without inheriting their failure modes? We argue that formal verification offers a principled escape from this dilemma, yet its adoption has been hindered by a critical bottleneck: the translation from natural language requirements to formal specifications. This paper bridges this gap by proposing , a neuro-symbolic framework that employs a bidirectional **Formal-of-Thought** architecture: LLMs serve as *specification compilers* that top-down decompose high-level human intent into atomic, verifiable constraints, then bottom-up prove compliance using Dafny specifications and Z3 Satisfiability modulo theories solving, which produces mathematical guarantees rather than probabilistic scores. We validate across three benchmarks spanning behavioral safety, multi-domain constraint adherence, and agentic upward deception detection. Experiments on 7 agent models demonstrate that achieves an average improvement of **16.6%** over LLM-as-a-Judge baselines, enables *weak-to-strong* generalization where a 7B judge achieves over 90% accuracy detecting deception from 72B agents, and provides *near-linear safety improvement* through iterative refinement.

Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existing benchmarks for AI agents in cybersecurity focus mainly on measuring proficiency–how effectively agents can complete offensive security tasks–but neglect a critical question: when and how should agents refuse harmful requests? We present the first framework for establishing refusal boundaries in offensive security contexts. Our framework defines (1) principled criteria for when tasks should be refused, (2) categories of tasks that warrant refusal, and (3) evaluation methodology for measuring agent robustness under both benign and adversarial conditions. We apply this framework to assess how current LLM-powered agents adhere to appropriate refusal boundaries across a range of web-based offensive security scenarios, finding that 6 of 8 frontier models tested refuse to identify vulnerabilities in real systems 0\% of the time.

Autonomous data science has been a long-standing challenge, and is now becoming feasible with the emergence of powerful large language models (LLMs). Recent workflow-based data agents have shown promising results on specific data tasks but remain fundamentally limited in achieving full autonomy due to their reliance on predefined workflows. In this paper, we introduce DeepAnalyze, the first agentic LLM for autonomous data science, capable of automatically completing the end-to-end data science from raw data to research reports. To tackle high-complexity data science tasks, we propose a curriculum-based agentic training paradigm that emulates the learning trajectory of human data scientists, enabling LLMs to progressively acquire and integrate multiple capabilities in real-world environments. Accordingly, we contribute a data-grounded trajectory synthesis framework to constructs high-quality data science training data. Through training in real-world environment, DeepAnalyze learns to perform a broad spectrum of data tasks, ranging from data question answering to open-ended data research. Experiments on 13 benchmarks demonstrate that, with only 8B parameters, DeepAnalyze outperforms workflow-based agents built on advanced proprietary LLMs. DeepAnalyze is fully open-sourced, paving the way toward autonomous data science.

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these complex settings. Our key innovation is an efficient online training process that ensures stable and effective policy improvement and . By leveraging policy mirror descent (PMD) to define an ideal, regularized target policy distribution, we frame the policy update as a distributional matching problem, training the expressive diffusion model to replicate this stable target. This decoupled approach stabilizes learning and significantly enhances training performance. Our method achieves state-of-the-art results and superior sample efficiency across a diverse set of challenging combinatorial benchmarks, including DNA sequence generation, RL with macro-actions, and multi-agent systems. Experiments demonstrate that our diffusion policies attain comparable or superior performance compared to other baselines. Crucially, our extensive empirical analysis reveals a key trade-off: FKL demonstrates superior sample efficiency and faster initial convergence, whereas RKL ensures stable training and higher asymptotic performance on challenging tasks.

While deep learning-based weather forecasting paradigms have made significant strides, addressing extreme weather diagnostics remains a formidable challenge. This gap exists primarily because the diagnostic process demands sophisticated multi-step logical reasoning, dynamic tool invocation, and expert-level prior judgment. Although agents possess inherent advantages in task decomposition and autonomous execution, current architectures are still hampered by critical bottlenecks: inadequate expert knowledge integration, a lack of professional-grade iterative reasoning loops, and the absence of fine-grained validation and evaluation systems for complex workflows under extreme conditions. To this end, we propose HVR-Met, a multi-agent meteorological diagnostic system characterized by the deep integration of expert knowledge. Its central innovation is the ``Hypothesis-Verification-Replanning'' closed-loop mechanism, which facilitates sophisticated iterative reasoning for anomalous meteorological signals during extreme weather events. To bridge gaps within existing evaluation frameworks, we further introduce a novel benchmark focused on atomic-level sub-tasks. Experimental evidence demonstrates that the system excels in complex diagnostic scenarios.

Visual agents employ external visual tools within visual chains of thought to incorporate fine-grained evidence. While prior work has mainly studied these tools in visual search tasks, their role in more complex visual reasoning remains underexplored. In this paper, we move beyond simple visual search tasks to investigate more challenging tasks, including 3D spatial reasoning and medical visual question answering, where agents must integrate tool-acquired local evidence with the global context. We identify a \emph{tool-use collapse phenomenon}: models progressively stop using tools while still achieving higher task accuracy. Moreover, we observe a clear asymmetry: (i) completely eliminating tool use degrades performance, whereas (ii) incentivizing tool use yields only marginal gains despite substantially increasing usage. We find that vanilla training and tool-use encouragement both reduce rollout diversity, explaining why higher tool use does not yield stronger reasoning performance. Motivated by these findings, we add an entropy regularization term to encourage diverse rollout exploration, achieving the best performance despite gradually declining tool usage. Overall, our findings suggest a training-time view of tools as scaffolding, where broader exploration over language generation and visual tool invocation improves reasoning despite tool-use collapse. Project page: https://scaffolded-exploration.github.io

Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder designed to address this challenge. DockSmith treats environment construction not merely as a preprocessing step, but as a core agentic capability that exercises long-horizon tool use, dependency reasoning, and failure recovery, yielding supervision that transfers beyond Docker building itself. DockSmith is trained on large-scale, execution-grounded Docker-building trajectories produced by a SWE-Factory--style pipeline augmented with a loop-detection controller and a cross-task success memory. Training a 30B-A3B model on these trajectories achieves open-source state-of-the-art performance on Multi-Docker-Eval, with 39.72\% Fail-to-Pass and 58.28\% Commit Rate. Moreover, DockSmith improves out-of-distribution performance on SWE-bench Verified, SWE-bench Multilingual, and Terminal-Bench 2.0, demonstrating the broader agentic benefits of environment construction. Our model and Docker-building trajectories are publicly available at https://huggingface.co/JiaranZhang/DockSmith.

Large Language Models (LLMs) have shown strong potential in complex medical reasoning yet face diminishing gains under inference scaling laws. While existing studies augment LLMs with various knowledge types, it remains unclear how effectively the additional costs translate into accuracy. In this paper, we explore how meta-cognition of LLMs, i.e., their self-assessment of their own cognitive states, can regulate the reasoning process. Specifically, we propose MedCoG, a Medical Meta-Cognition Agent with Knowledge Graph, where the meta-cognitive assessments of task complexity, familiarity, and knowledge density dynamically regulate utilization of procedural, episodic, and factual knowledge. The LLM-centric on-demand reasoning aims to mitigate the diminishing returns under scaling law by (1) reducing costs via avoiding indiscriminate scaling, (2) improving accuracy via filtering out distractive knowledge. To validate this, we empirically characterize the scaling curve and introduce inference density to quantify inference efficiency. Experiments demonstrate the effectiveness and efficiency of MedCoG on five hard sets of medical benchmarks, yielding 6.2x inference density. Furthermore, the Oracle study highlights the significant potential of meta-cognitive regulation.

Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to address this limitation through various approaches, among which increasing reflective diversity has shown promise. Our empirical analysis reveals a strong positive correlation between reflective diversity and task success, further motivating the need for diverse reflection signals. We introduce `ParamMem`, a parametric memory module that encodes cross-sample reflection patterns into model parameters, enabling diverse reflection generation through temperature-controlled sampling. Building on this module, we propose ParamAgent, a reflection-based agent framework that integrates parametric memory with episodic and cross-sample memory. Extensive experiments on code generation, mathematical reasoning, and multi-hop question answering demonstrate consistent improvements over state-of-the-art baselines. Further analysis reveals that `ParamMem` is sample-efficient, enables weak-to-strong transfer across model scales, and supports self-improvement without reliance on stronger external model, highlighting the potential of `ParamMem` as an effective component for enhancing language agents.

Multimodal Large Language Model (MLLM) agents facilitate Graphical User Interface (GUI) automation but struggle with long-horizon, cross-application tasks due to limited context windows. While memory systems provide a viable solution, existing paradigms struggle to adapt to dynamic GUI environments, suffering from a granularity mismatch between high-level intent and low-level execution, and context pollution where the static accumulation of outdated experiences drives agents into hallucination. To address these bottlenecks, we propose the Darwinian Memory System (DMS), a self-evolving architecture that constructs memory as a dynamic ecosystem governed by the law of "survival of the fittest." DMS decomposes complex trajectories into independent, reusable units for compositional flexibility, and implements Utility-driven Natural Selection to track survival value, actively pruning suboptimal paths and inhibiting high-risk plans. This evolutionary pressure compels the agent to derive superior strategies. Extensive experiments on real-world multi-app benchmarks validate that DMS boosts general-purpose MLLMs without training costs or architectural overhead, achieving average gains of 18.0% in success rate and 33.9% in execution stability, while reducing task latency, establishing it as an effective self-evolving memory system for GUI tasks. The implementation is available at https://anonymous.4open.science/r/DMS-C48C.