ICML 2026 论文列表

Recent large language models (LLMs) have demonstrated strong capabilities across challenging tasks, enabling their widespread adoption in agentic systems that interact with external tools. In such deployments, however, LLMs are typically trained with general-purpose tokenizers designed for broad language coverage, while their usage is dominated by narrow, structured tool-calling interactions. This training–deployment mismatch leads to inefficient tokenization, where repetitive structural patterns and frequent semantic units in function calls are fragmented into long sequences of low-level tokens, increasing decoding overhead. To address this gap, we introduce $\textbf{AgentVocab}$, a structure-aware vocabulary adaptation framework for efficient LLM agents. AgentVocab derives specialized vocabulary entries from real tool-calling traces and adapts the model vocabulary to better reflect structural and semantic regularities, without task-specific schema engineering. Experiments on $\tau$-bench and $\tau^2$-bench show that AgentVocab preserves tool-calling performance while reducing latency relative to the vanilla baseline by 17.7\% and 19.5\%, respectively. Our approach is orthogonal to existing fine-tuning and agent-training methods and integrates seamlessly into standard agent pipelines. Source code and models will be available at https://github.com/Starry-159/AgentVocab.

Modern language models reason within bounded context, an inherent constraint that poses a fundamental barrier to long-horizon reasoning. We identify recursion as a core principle for overcoming this barrier, and propose recursive models as a minimal realization, where the model can recursively invoke itself to solve subtasks in isolated contexts. We prove that any computable problem admits a recursive decomposition of reasoning in which each subtask requires only exponentially smaller active context than standard autoregressive models; this strictly surpasses any context management approach confined to a single sequence, such as summarization. We further generalize our framework to modern agentic systems with arbitrary context processing and control flows, and prove that recursive models can achieve optimal power within this broader class. Experimentally, we train a 3B model to reason recursively and evaluate on Boolean satisfiability, a task requiring long-horizon combinatorial search, where it significantly outperforms frontier LLMs.

Parallelizing code for **irregular data structures** (sparse graphs, unbalanced trees, non-uniform meshes) is notoriously hard, and current LLMs fail catastrophically on such tasks, generating code riddled with race conditions, deadlocks, and poor scaling. We address this with **ParEVO**, a framework for synthesizing high-performance parallel algorithms for irregular data, built on three contributions: the **Parlay-Instruct Corpus** of 13,820 tasks generated via a "Critic-Refine" pipeline that filters for empirically performant uses of Work-Span primitives; specialized **DeepSeek**, **Qwen**, and **Gemini** models fine-tuned to the semantics of the ParlayLib library; and an **Evolutionary Coding Agent (ECA)** that repairs the "last mile" of correctness using compiler and profiler feedback. On the ParEval benchmark, ParEVO achieves an average **107x speedup** and a **13.6x speedup** on highly complex irregular graph problems, outperforming commercial models like GPT-5-Thinking and Gemini-3-Pro, while matching expert *human-written* baselines and reaching up to a **4.1x speedup** on kernels such as Maximal Independent Set. This demonstrates that AI-driven agents can effectively navigate the complex landscape of high-performance computing. Source code and datasets are available at https://github.com/WildAlg/ParEVO.

Sentence representations are foundational to many Natural Language Processing (NLP) applications. While recent methods leverage Large Language Models (LLMs) to derive sentence representations, most rely on final-layer hidden states, which are optimized for next-token prediction and thus often fail to capture global, sentence-level semantics. This paper introduces a novel perspective, demonstrating that attention value vectors capture sentence semantics more effectively than hidden states. We propose *Value Aggregation (VA)*, a simple method that pools token values across multiple layers and token indices. In a training-free setting, VA outperforms other LLM-based embeddings, even matches or surpasses the ensemble-based MetaEOL. Furthermore, we demonstrate that when paired with suitable prompts, the layer attention outputs can be interpreted as aligned weighted value vectors. Specifically, the attention scores of the last token function as the weights, while the output projection matrix ($W_O$) aligns these weighted value vectors with the common space of the LLM residual stream. This refined method, termed *Aligned Weighted VA (AlignedWVA)*, achieves state-of-the-art performance among training-free LLM-based embeddings, outperforming the high-cost MetaEOL by a substantial margin. Finally, we highlight the potential of obtaining strong LLM embedding models through fine-tuning Value Aggregation.

Rich-format documents are essential for everyday operations yet costly to author, motivating the need for automated generation to enhance productivity. To this end, we present FormAct, an agentic system that generates professional rich-format documents from scratch. FormAct operates on an HTML source representation and performs iterative source refinement with an *editing agent* that invokes a suite of tools, including a syntax-aware source editor and a template retriever, and a *review agent* that critiques rendered pages to guide refinement. Additionally, we incorporate edit-triggered context compression to maintain a bounded working context and keep multi-round editing efficient. To support development and evaluation, we introduce RichDocBench for end-to-end generation, and RichDocFuzz to evaluate formatting-error recognition for reviewer agents. Through extensive automated evaluation and blind human-preference studies, we show that FormAct consistently outperforms strong baselines, including Codex-CLI, with particularly strong improvements in generating error-free, professional rich-format documents.

Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applications. Yet an overlooked threat is Reasoning-Level Denial-of-Service (R-DoS), in which an attacker preserves task correctness but degrades availability by inflating an agent’s reasoning depth or tool-use budget. We introduce OTora, the first unified, two-stage red-teaming framework for instantiating R-DoS attacks. Stage I optimizes an adversarial trigger that induces targeted tool invocations using insertion-aware scoring and dynamic target co-evolution, supporting both black-box and white-box settings. Stage II generates agent-aware reasoning payloads via an ICL-guided genetic search that amplifies overthinking while maintaining correct task outcomes. Across WebShop, Email, and OS agents built on multiple backbone models such as LLaMA-70B and GPT-OSS-120B, OTora achieves up to 10× increases in reasoning tokens and order-of-magnitude latency slowdowns, all while preserving near-baseline task accuracy. Finally, we discuss mitigation strategies for detecting and constraining abnormal reasoning and latency spikes.

Tokenization is the first point of contact between large language models (LLMs) and text data, yet it has not been viewed by many as a component of LLMs worth accelerating. During inference, tokenizers typically rely on simple dictionary lookups and are executed on CPUs as standard processes. This approach, however, introduces significant overhead from scheduling delays, core selection, data copying, and other system-level costs. These inefficiencies become problematic in latency-sensitive applications such as embedding, small language models, and agentic AI. In this paper, we present the Pinned Tokenizer (PinTok), a novel tokenizer architecture that reduces redundant hardware, operating system, and networking overhead through three key innovations: core and memory pinning, scheduling and context switch avoidance, and duplicate network packet copy and processing avoidance. Our implementation of PinTok can serve as a drop-in replacement for existing tokenizer deployments, delivering latency reductions of up to 95% (average), 97% (P50), 94% (P90), and 87% (P99) along with throughput improvements of up to 2,084%.

Large language models (LLMs) have demonstrated exceptional capabilities when trained within executable runtime environments, notably excelling at software engineering tasks through verified feedback loops. Yet, scalable and generalizable execution-grounded environments remain scarce, limiting progress in training more capable ML agents. We introduce CTF-Dojo, the first large-scale executable runtime tailored for training LLMs with verifiable feedback, featuring 658 fully functional Capture-The-Flag (CTF)-style challenges containerized in Docker with guaranteed reproducibility. To enable rapid scaling without manual intervention, we develop CTF-Forge, an automated pipeline that transforms publicly available artifacts into ready-to-use execution environments in minutes, eliminating weeks of expert configuration traditionally required. We trained LLM-based agents on just 486 high-quality, execution-verified trajectories from CTF-Dojo, achieving up to 11.6% absolute gains over strong baselines across three competitive benchmarks: InterCode-CTF, NYU CTF Bench, and Cybench. Our best-performing 32B model reaches 31.9% Pass@1, establishing a new open-weight state-of-the-art that rivals frontier models like DeepSeek-V3-0324 and Gemini-2.5-Flash. By framing CTF-style tasks as a benchmark for executable-agent learning, CTF-Dojo demonstrates that execution-grounded training signals are not only effective but pivotal in advancing high-performance ML agents without dependence on costly proprietary systems.

While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conversation-level collaborative studies lack grounded interaction and behavioral execution, motivating the need for cooperative game environments that enable contextualized and immersive collaboration. To this end, this paper proposes CollabBench, a benchmark for evaluating and training collaborative agents in cooperative games. CollabBench features a Diverse Player Profile Simulation pipeline to model varied players behaviors, and a Collaborative Agentic Training paradigm that unifies reasoning, communication, and action via agentic rollouts, optimized with a hybrid reward balancing task efficiency and affective adaptation. We further extend classic environments to CWAH-MultiPlayer and Cook-MultiPlayer for systematic evaluation under diverse personalities. Experiments with efficiency and affective metrics show that our trained models outperform base models, achieving 19.5% higher efficiency and 24.4% improved affective performance. Further analysis reveals key collaborative limitations of existing models and offers insights for future collaborative training.

Recent advances in generative video models have blurred the boundary between real and synthetic content, raising urgent concerns about digital authenticity. Multimodal large language models (MLLMs) are appealing for AI-generated video (AIGV) detection due to their broad perceptual and reasoning capabilities; however, existing MLLM-based detectors still suffer from hallucination and unstable reasoning, leading to high false-alarm rates and generic, non-verifiable explanations. To address these issues, we propose Hermes, an evidence-driven agentic framework for trustworthy and explainable AIGV detection. Hermes realizes three key capabilities: (1) Adaptive Instance-Conditioned Detection Strategy Planning, (2) Evidence-Centric Reasoning and Verification, and (3) Graph-Grounded Evidence Deliberation. Specifically, Hermes uses instance-conditioned retrieval-augmented generation to analyze each video and retrieve authenticity-verification knowledge for composing a tailored detection strategy. It then constructs a verifiable Evidence Reasoning Graph (ERG) to keep reasoning grounded in concrete video evidence and reduce attention drift. Finally, multi-agent deliberation audits and refines the ERG to reconcile conflicting evidence and improve reliability. With these capabilities and a library of forensic tools, Hermes enables structured, verifiable, and interpretable decision-making. Extensive experiments show that Hermes achieves state-of-the-art performance while producing auditable explanations for trustworthy video forensics.

Speech Large Language Models (SLLMs) enable high-level emotion reasoning, but often produce ungrounded, text-biased judgments without verifiable acoustic evidence. In contrast, SSL encoders such as WavLM yield strong acoustic representations yet remain opaque discriminative models that offer limited interpretability. To bridge this gap, we introduce the Agentic Decoding of Emotion via Probing Tools (ADEPT) framework, which reframes emotion recognition as a multi-turn inquiry process rather than a single-pass prediction. ADEPT transforms an SLLM into an agent that maintains an evolving candidate set and adaptively invokes dedicated semantic and acoustic probing tools within a structured pipeline of candidate generation, evidence collection, and adjudication. Crucially, ADEPT enables a paradigm shift from consensus learning to ambiguity-driven emotion reasoning. Since human affect exhibits complexity and co-occurrence of emotions, we leverage minority annotations as informative signals instead of discarding them as noise. Finally, we integrate Group Relative Policy Optimization (GRPO) with the Evidence Trust Gate to explicitly couple tool-usage behaviors with prediction quality and enforce evidence-based reasoning. Experiments demonstrate that ADEPT improves in most cases the primary emotion accuracy while substantially improving minor emotion characterization, producing explanations grounded in auditable evidence.

Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting their ability to identify sparse yet critical evidence amid extensive redundancy. We introduce Video-o3, a novel framework that supports iterative discovery of salient visual clues, fine-grained inspection of key segments, and adaptive termination once sufficient evidence is acquired. Technically, we address two core challenges in interleaved tool invocation. First, to mitigate attention dispersion induced by the heterogeneity of reasoning and tool-calling, we propose Task-Decoupled Attention Masking, which isolates per-step concentration while preserving shared global context. Second, to control context length growth in multi-turn interactions, we introduce a Verifiable Trajectory-Guided Reward that balances exploration coverage with reasoning efficiency. To support training at scale, we further develop a data synthesis pipeline and construct Seeker-173K, comprising 173K high-quality tool-interaction trajectories for effective supervised and reinforcement learning. Extensive experiments show that Video-o3 substantially outperforms state-of-the-art methods, achieving 72.1% accuracy on MLVU and 46.5% on Video-Holmes. These results demonstrate Video-o3's strong multi-hop evidence-seeking and reasoning capabilities, and validate the effectiveness of native tool invocation in long-video scenarios.

LLM-based agents already operate in production across many industries, yet we lack an understanding of what technical methods make deployments successful. We present the first systematic study of **M**easuring **A**gents in **P**roduction, MAP, using first-hand data from agent developers. We conducted 20 case studies via in-depth interviews and surveyed 86 deployed systems practitioners across 26 domains. We investigate why organizations build agents, how they build them, how they evaluate them, and their top development challenges. Our study finds that production agents are built using simple, controllable approaches: 68% execute at most 10 steps before human intervention, 70% rely on prompting off-the-shelf models instead of weight tuning, and 74% depend primarily on human evaluation. Reliability (consistent correct behavior over time) remains the top development challenge, which practitioners currently address through systems-level design. MAP documents the current state of production agents, providing the research community with visibility into deployment realities and underexplored research avenues.

Agentic reasoning enables large reasoning models (LRMs) to dynamically acquire external knowledge, yet optimizing the retrieval process remains challenging due to the lack of dense, principled reward signals. In this paper, we introduce *InfoReasoner*, a unified framework that incentivizes effective information seeking via a *synthetic semantic information gain reward*. Theoretically, we redefine information gain as uncertainty reduction over the model's belief states, establishing key properties including non-negativity, telescoping additivity, and channel monotonicity. Practically, to enable scalable optimization without manual intermediate retrieval annotations, we instantiate this principle as a semantic information gain reward computed from the model's output distributions using *semantic clustering via bidirectional textual entailment*. This training reward provides dense credit for retrieval steps while remaining anchored to final-answer correctness, enabling efficient training via Group Relative Policy Optimization (GRPO). Experiments on seven question-answering benchmarks, MATH500, and WebDetective show consistent gains over strong retrieval-augmented baselines, supporting our dense semantic information gain as a practical training signal for agentic retrieval.

LLM agents powered by retrieval and RAG are increasingly prevalent across research and applications. Embedding models play a critical role in these systems, particularly in embedding-based retrieval. However, current benchmarks for embeddings remain focused on general-purpose scenarios, which may fail to align well with the diverse and evolving needs of agentic applications. To close this gap, we introduce Agent-Oriented Embedding Benchmark (AOEB), a comprehensive evaluation suite dedicated to agent-centric retrieval for embedding models. AOEB is characterized by two key features: (1) Multi-Task, covering five essential capabilities for retrieval in LLM agents, including code, tool, reasoning, and memory retrieval; and (2) Multi-Modal, providing evaluation with both textual and visual data for each task category. We evaluate representative embedding models on AOEB and observe that they exhibit distinct strengths across different agent-oriented retrieval tasks. By curating AOEB, we aim to promote a move toward more practically oriented directions within the embedding community and foster further progress.

Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, yet its practical accessibility and scalability is often constrained by container-based execution frameworks used for environment isolation. As the number of task instances increases, pre-cached container images introduce substantial storage overhead, limiting large-scale training under limited cotainer resources, and excludes users without container management privileges. We introduce SWE-MiniSandbox, a lightweight, container-free method that enables scalable RL training of SWE agents without sacrificing isolation. Instead of relying on per-instance containers, SWE-MiniSandbox executes each task in an isolated workspace backed by kernel-level mechanisms, substantially reducing system overhead. It leverages lightweight environment pre-caching techniques to eliminate the need for bulky container images. As a result, our approach lowers disk usage to approximately 5\% of that required by container-based pipelines and reduces environment preparation time to about 25\% of the container baseline. Empirical results demonstrate that SWE-MiniSandbox achieves evaluation performance comparable to standard container-based pipelines. Consequently, by removing the dependency on heavy container infrastructure, SWE-MiniSandbox offers a practical and accessible foundation for scaling RL-based SWE agents, particularly in resource-constrained research environments.

As large language models (LLMs) improve in mathematical reasoning and formal understanding, a promising approach for automated theorem proving (ATP) is to enable LLMs construct proof sketches, which plan a high-level proof strategy and decompose complex theorems into independently provable subgoals. However, most existing proof sketches are immutable. As a result, any revision typically requires rebuilding the entire sketch, which discards already proved subgoals and bring additional cost. In this paper, we address this limitation by introducing EditableSketch, an editable proof-sketch structure that supports in-place edits for error correction and further subgoal decomposition while preserving previously proved subgoals. Building on EditableSketch, we introduce SketchRefine, a proof-generation framework for ATP by iteratively refining proof sketches through localized, incremental edits. Experiments show that our method not only reduces the cost of the proof process, but also achieves superior performance. For example, our method realizes 76.0% pass rate on FormalMath-Lite (+14.1\% vs. DeepSeek-Prover-V2-671B). Meanwhile, compared with Hilbert, our method significantly reduces token overhead while achieving comparable performance.

Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning, often leading to inefficient exploration and sparse rewards. To mitigate this issue, we propose Expert-Assisted Policy Optimization (EAPO), a novel RL framework that enhances exploration by incorporating multi-turn interactions with external experts during training. Unlike prior methods, where policies reason in isolation, EAPO incentivizes the policy to adaptively determine when and how to consult experts, yielding richer reward signals and more reliable reasoning trajectories. External assistance ultimately internalizes expert knowledge into the policy model, amplifying the model’s inherent reasoning capabilities. During evaluation, the policy model has been well-optimized to solve questions independently, producing improved reasoning paths and more accurate solutions. On AIME 2024/2025 and AIMO 2025, EAPO consistently outperforms expert-assisted, expert-distilled, and RL baselines, averaging a 5-point gain over self-exploration RL, and also generalizes to non-math benchmarks, including HumanEval, HLE, GPQA, MMLU, EvalPlus, HotpotQA, and SimpleQA.

As the reasoning capabilities of Large Language Models (LLMs) expand, evaluating true inductive generalization on entirely unseen data becomes increasingly challenging. To this end, we introduce a modular in-context learning evaluation framework, that is scalable and extendable across its separate modules. This is based upon the notion of synthetic scenarios with controllable complexity across three independent axes: 1) the logic of the underlying data distribution (UDD) 2) their projection into diverse representations, and 3) the interaction dynamic determining how the model accesses and explores the data. For these scenarios, the model is tasked to perform in-context scientific discovery and produce an interpretable theory in natural language that explains the observations. In a separate conversation, the model is then tasked to convert this generated theory into executable code, which can be programmatically compared against the underlying data distribution. Using this modular framework we produce an initial suite of 600 diverse scenarios that we use to evaluate and analyze various state-of-the-art LLMs. Although these experiments show that Gemini 3.0 Pro achieves the best overall score, each model performs the best at different tasks. For example: GPT 5.2 is the clear winner on pure symbolic data, Claude Opus 4.5 is the best at working with files, Gemini is the strongest model for the non-dynamic scenarios, and Grok 4.1 is the strongest model when UDD complexity scales. Furthermore, all models struggle with active exploration and are seemingly incapable of identifying informative data points, resulting in less efficient exploration than a random baseline.