ICML 2026 论文列表

High-performance GPU kernels are critical for efficient LLM serving, yet their optimization remains a bottleneck requiring deep system expertise. While code LLMs show promise in generating functionally correct code, kernel optimization is intrinsically a search problem over a vast optimization space. This fundamental mismatch prevents existing LLM agents from efficiently exploring the optimization space for diverse hardware and compute patterns. To bridge the gap, we present KernelBand, a framework that formulates kernel optimization as a Multi-Armed Bandit (MAB) problem, explicitly balancing exploration and exploitation to unlock the potential of code LLMs. To navigate the infinite arm space of optimization strategies applied to candidate kernels, we design two key mechanisms: a hardware-aware pruning strategy via profiling bounds and a runtime-behavior clustering algorithm that leverages Lipschitz continuity. Extensive experiments on TritonBench-G with three GPU architectures and four code LLMs show that KernelBand consistently outperforms the strongest available agent baseline, achieving up to **1.91×** geometric mean speedup over correctly optimized kernels with **39–140%** relative improvement in Fast@1 success rate. Our code is available at https://github.com/TongmingLAIC/KernelBand.

We study decentralized multi-agent reinforcement learning (MARL) for networked service systems with affinity in the presence of Byzantine nodes. The way that a server processes a job depends on an affinity state that captures the correlation between the job and the server. Each node learns a local control policy via an actor-critic algorithm with linear function approximation over inherently unbounded space of traffic states, while exchanging parameter information with neighbors through a communication graph. A set of Byzantine agents can exploit the unbounded state space to compromise the consensus mechanism, destabilizing both learning and queuing processes. To address this vulnerability, we propose a resilient consensus-based MARL algorithm, which mitigates adversarial parameter manipulation and guarantees traffic stability under mild assumptions. We prove that the cooperative agents’ policies converge almost surely to a bounded neighborhood of a stationary solution of the global objective. We demonstrate the effectiveness and generality of the proposed framework in several representative service systems, including semantic routing for large language model serving, distributed polling in cloud computing, and smart manufacturing logistics.

The rapid development of Large Language Models has driven Multi-Agent Systems (MAS) growth, but constructing efficient MAS requires labor-intensive manual design. Current automation methods generate templated agents, use monolithic optimization, and ignore task complexity gradients. This paper presents Evolutionary MAS (EvoMAS), a biologically-inspired framework whose core is a dynamic and diverse repertoire of seven evolutionary strategies---six biologically-inspired operators (3 exploration, 3 exploitation) together with a custom operator for domain-specific transformations---driven by adaptive strategy selection. These are complemented by role-level evolution that refines agent specialization and collaboration patterns, and a curriculum-guided schedule that evolves workflows from simple to complex tasks with cross-stage stability. Additionally, to resolve the contradiction between the inefficiency of pure evolution and the rigidity of manual design, we introduce the *Cyber Creator*, a meta-controller that conducts heuristics-in-the-loop learning by formulating and reflectively updating evolutionary rules and strategies. Evaluations demonstrate that EvoMAS consistently outperforms existing methods across multiple domains while maintaining cost efficiency, with roles evolving from homogeneous actors to specialized reasoning ensembles.

Multi-modal neuroimaging-based psychiatric diagnosis must integrate cross-modal agreement with modality-specific complementarity, yet in real multi-site cohorts these signals are frequently entangled with site- and cohort-dependent correlations, yielding shortcut-driven predictions and limited interpretability. We propose Structured Multi-modal Graph Disentanglement (SMGD), which explicitly factorizes multi-modal graph representations into four components with distinct roles: shared diagnostic evidence, complementary diagnostic evidence, incidental cross-modal agreement, and modality-specific non-robust correlations, with the former two forming the diagnostic core and the latter two suppressed as shortcuts. SMGD is realized as geometry-driven structure learning: under a mild distributional assumption, we develop mini-batch estimable surrogate regularizers that shape subspace organization and cross-modal relations, enforcing semantic consistency through relational geometry rather than centroid coincidence while suppressing confounded dependencies. Experiments on large multi-site datasets show improved in-domain diagnosis and more reliable cross-dataset generalization in the presence of a Modality Gap, without relying on expert-crafted diagnostic biomarkers.

We study the problem of learning Nash equilibria in offline two-player zero-sum Markov games. While existing approaches often rely on explicit pessimism to address distribution shift, we show that KL regularization alone suffices to stabilize learning and guarantee convergence. We first introduce Regularized Offline Sequential Equilibrium (ROSE), a theoretical framework that achieves a fast $ \widetilde{\mathcal{O}}(1/n) $ convergence rate under *unilateral concentrability*, improving over the standard $ \widetilde{\mathcal{O}}(1/\sqrt{n}) $ rates in unregularized settings. We then propose Sequential Offline Self-play Mirror Descent (SOS-MD), a practical model-free algorithm based on least-squares value estimation and iterative self-play updates. We prove that the last iterate of SOS-MD attains the same $ \widetilde{\mathcal{O}}(1/n) $ statistical rate up to a vanishing optimization error of order $ \widetilde{\mathcal{O}}(1/\sqrt{T}) $ in the number of self-play iterations $T$.

Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results. To improve robustness and solution quality, recent approaches deploy multiple agent teams running in parallel to explore diverse reasoning trajectories. However, parallel execution comes at a significant computational cost: when different teams independently reason about similar sub-problems or execute analogous steps, they repeatedly perform substantial overlapping computation. To address these limitations, in this paper, we propose Learning to Share (LTS), a learned shared-memory mechanism for parallel agentic frameworks that enables selective cross-team information reuse while controlling context growth. LTS introduces a global memory bank accessible to all teams and a lightweight controller that decides whether intermediate agent steps should be added to memory or not. The controller is trained using stepwise reinforcement learning with usage-aware credit assignment, allowing it to identify information that is globally useful across parallel executions. Experiments on the AssistantBench and GAIA benchmarks show that LTS significantly reduces overall runtime while matching or improving task performance compared to memory-free parallel baselines, demonstrating that learned memory admission is an effective strategy for improving the efficiency of parallel agentic systems.

In recent years, LLM-based multi-agent systems (MAS) have advanced rapidly, using a router to decompose tasks and delegate subtasks to specialized agents. A natural way to expand capability is to scale up the agent pool by continually integrating new functional agents or tool interfaces, but naive expansion can trigger performance collapse when the router cold-starts on newly added, heterogeneous, and unreliable agents. We propose MonoScale, an expansion-aware update framework that proactively generates a small set of agent-conditioned familiarization tasks, harvests evidence from both successful and failed interactions, and distills it into auditable natural-language memory to guide future routing. We formalize sequential augmentation as a contextual bandit and perform trust-region memory updates, yielding a monotonic non-decreasing performance guarantee across onboarding rounds under a non-interfering expansion assumption. Experiments on GAIA and Humanity's Last Exam show stable gains as the agent pool grows, outperforming naive scale-up and strong-router fixed-pool baselines. Our code is available here.

Existing contrastive multi-view clustering methods rely on a pre-defined cluster number, limiting their flexibility in real-world scenarios lacking prior knowledge. To address this, we propose GROK, a novel framework driven by a cluster decision agent for unknown-$K$ multi-view clustering. It pioneers the adaptation of group relative policy optimization (GRPO) —a reinforcement learning strategy for LLM reasoning— into the unsupervised domain to autonomously determine the optimal $K$. Specifically, the agent orchestrates the clustering process through three synergistic phases. First, in the state perception phase, we employ a structure-aware adaptive backbone to aggregate multi-view data, providing the agent with consistent and discriminative consensus observations. Second, in the group decision phase, we introduce an action space divide-and-conquer strategy and an adaptive reward function. Equipped with these mechanisms, the agent performs group sampling and relative advantage estimation within the discrete action space of candidate $K$ values, autonomously searching for the optimal $K$ via reward maximization. Finally, via geometric feedback, geometric clustering guidance mechanism transforms the agent's structural hypotheses into explicit differentiable constraints to reshape feature manifolds, thereby closing the perception-decision-feedback loop. Experimental results demonstrate that GROK achieves superior clustering performance in unknown-$K$ scenarios by autonomously exploring the cluster structure.

Multi-turn, multi-agent LLM game evaluations exhibit substantial run-to-run variance. In long-horizon interactions, small deviations compound across turns and are amplified by multi-agent coupling, biasing win rate estimates and destabilizing comparative rankings across repeated tournaments. Prompt choice exacerbates this by inducing different effective policies and interaction dynamics. We address both instability and underperformance in games with **MEMO:** (**Me**mory-augmented **MO**del context optimization), a self-play framework that treats inference-time context as an optimizable, agentic object by coupling **retention** and **exploration**. Retention distills self-play trajectories into a persistent memory bank of structured insights that act as priors; exploration combines tournament-style prompt evolution under TrueSkill with prioritized replay over decisive states. Across five text-based games and a 2,000-game budget per task, MEMO raises mean win rate from 25.1% to 49.5% for GPT-4o-mini and from 20.9% to 45.0% for Qwen-2.5-7B, while sharply reducing run-to-run dispersion. These results suggest substantial headroom in multi-agent LLM game performance and robustness can be unlocked through memory, with MEMO achieving gains in negotiation and imperfect-information settings, while RL remains more effective in perfect-information settings. Project website: https://yunfeixie233.github.io/MEMO/.

This paper studies a fundamental yet often overlooked premise in evolutionary multi-view classification (EMVC): the impact of label noise on EMVC, such as distorting fitness landscapes shaped by individual fitness values (e.g., test accuracy). Traditional EMVC assumes training labels are noise-free, yet this often fails in practice. As a result, label noise introduces harmful supervision during the training phase, resulting in distorted fitness landscapes and the emergence of fitness evaluation bias (FEB). This bias misguides the evolutionary trajectory, causing the search process to stagnate in local optima. Given that label noise largely stems from the mislabeling of samples near their decision boundaries by human annotators, we thus compared the decision boundaries of human annotators and models, and found discrepancies between the two. Based on this observation, we propose a simple yet effective ``detect-then-calibrate" data purification framework that leverages outlier analysis in the gradient space (i.e., treating outliers as noisy samples) and prototype calibration in the feature space (i.e., utilizing feature prototypes of noise-free samples to correct the labels of noisy samples). Experimental results demonstrate that this strategy can effectively purify the data and alleviate FEB; moreover, it can improve the performance of various multi-view learning paradigms in label noise scenarios. (https://github.com/LiShuailzn/ICML-2026-GFD-EMVC)

Agentic Web is an emerging paradigm where autonomous agents help users use online information. As the paradigm develops, content providers are also deploying agents to manage their data and serve it through controlled interfaces. This shift moves information access from centralized retrieval to decentralized coordination. To study this setting, we introduce AgentWebBench, a benchmark that evaluates how well a user agent synthesizes answers by interacting with website-specific content agents. We evaluate four tasks that cover common web information needs, spanning ranked retrieval (web search, web recommendation) and open-ended synthesis (question answering, deep research). Across seven advanced LLMs and three coordination strategies, multi-agent coordination generally lags behind centralized retrieval as expected, because user agent cannot directly access the corpus, but the gap shrinks with model scale and can even outperform centralized retrieval on question answering. This benchmark also enables us to study properties of the emerging paradigm of the digital world. We find that decentralized access concentrates traffic toward a small set of websites, test time scaling improves both interaction reliability and task performance, and strong results require sufficient interactions guided by careful planning. Finally, our failure analysis suggests that user agents need better planning and answer synthesis, while content agents need more reliable retrieval and evidence quality. Code, data, and APIs are released on https://github.com/cxcscmu/AgentWebBench.

Recent progress in multi-turn reinforcement learning (RL) has significantly improved reasoning LLMs' performances on complex interactive tasks. Despite advances in stabilization techniques such as fine-grained credit assignment and trajectory filtering, instability remains pervasive and often leads to training collapse. We argue that this instability stems from inefficient exploration in multi-turn settings, where policies continue to generate low-information actions that neither reduce uncertainty nor advance task progress. To address this issue, we propose Token- and Turn-level Policy Optimization (T$^2$PO), an uncertainty-aware framework that explicitly controls exploration at fine-grained levels. At the token level, T$^2$PO monitors uncertainty dynamics and triggers a thinking intervention once the marginal uncertainty change falls below a threshold. At the turn level, T$^2$PO identifies interactions with negligible exploration progress and dynamically resamples such turns to avoid wasted rollouts. We evaluate T$^2$PO in diverse environments, including WebShop, ALFWorld, and Search QA, demonstrating substantial gains in training stability and performance improvements with better exploration efficiency. Code is available at https://github.com/WillDreamer/T2PO.

While the emerging field of agentic software engineering has spurred extensive research into post-training, this paradigm alone does not fully address the distribution mismatch between traditional static pre-training and dynamic deployment environments. In this paper, we instead investigate agentic mid-training as a scalable complementary approach. Central to our approach is *agent-native data* comprising two complementary components: *contextually-native trajectories* that preserve the complete information flow an agent experiences, offering broad coverage and diversity; and *environmentally-native trajectories* whose observations stem from actual tool invocations and test executions, providing interaction authenticity. On `SWE-Bench Verified`, our recipe outperforms the previous open software engineering mid-training recipe `Kimi-Dev` under two post-training settings with the same base model and agentic scaffold, while using fewer than half mid-training tokens (73.1B). Furthermore, our 32B and 72B models achieve state-of-the-art resolution rates of **56.1\%** and **58.5\%** among open agentic recipes using agentic scaffolds, despite starting from non-coder `Qwen2.5` base models. We also observe performance gains on general code generation and scientific benchmarks. We open-source a significant portion of our datasets, recipes, and model checkpoints to facilitate further research.

We study the online routing problem in large language model serving, where requests arrive sequentially and must be dispatched to parallel decode workers under tight batch-size and KV-cache constraints. Unlike widely used routing heuristics that are not tied to explicit service-level objectives (SLOs) and offer limited control over latency–throughput trade-offs, we introduce an multi-objective optimization framework that formulates routing as an online linear programming with interpretable decision rewards. We apply an efficient bid-price control policy based on the online linear programming that admits requests when their SLO-weighted benefit exceeds their shadow prices. To meet millisecond decision requirements, we develop a warm-started, projected first-order updates that track the evolving dual shadow prices online with predictable runtime. We integrate our router into the Vidur simulator and demonstrate substantial improvements over standard baselines across multiple SLO regimes, including end-to-end latency, time-to-first-token, throughput, and tail performance. A big picture from our result: a science-based approach outperforms others based on heuristics.

Evidential Deep Learning (EDL) enables trustworthy multi-view classification, yet suffers from a critical vulnerability: the Scale Mismatch Problem. We theoretically demonstrate that existing evidential fusion rules erroneously equate logit magnitude with semantic confidence, rendering them susceptible to semantic hijacking by inflated but uninformative views. To resolve this, we propose Scale-Invariant Evidential Fusion (SAEF), a framework utilizing instance-wise standardization to strictly decouple confidence from scale. Instead of relying on magnitude dominance, SAEF aggregates views based on statistical consensus. Theoretically, SAEF guarantees invariance to global scaling and robustness to asymmetric dominance. Experiments on four diverse datasets confirm that SAEF outperforms state-of-the-art baselines in accuracy and robustness to semantic conflicts and noise, ensuring stability against severe scale perturbations.

With the rapid progress of multi-agent large language model (LLM) reasoning, how to effectively aggregate answers from multiple LLMs has emerged as a fundamental challenge. Standard majority voting treats all answers equally, failing to consider latent heterogeneity and correlation across models. In this work, we design two new aggregation algorithms called Optimal Weight (OW) and Inverse Surprising Popularity (ISP), leveraging both first-order and second-order information. Our theoretical analysis shows these methods provably mitigate the inherent limitations of majority voting under mild assumptions, leading to more reliable collective decisions. We empirically validate our algorithms on synthetic datasets, popular LLM fine-tuning benchmarks such as UltraFeedback and MMLU, and a real-world healthcare setting ARMMAN. Our algorithms consistently outperform standard baselines, establishing a robust, training-free framework for effective multi-agent LLM aggregation.

Multi-agent systems (MAS) are increasingly capable of tackling complex real-world tasks, yet their reliance on inter-agent coordination, tool use, and long-horizon reasoning makes error recognition particularly challenging. Minor errors can propagate across agents, escalating into task failures while producing long, intertwined execution trajectories that impose significant costs for both human developers and automated systems to debug and analyze. Our key insight is that, despite surface differences in failure trajectories (e.g., logs), MAS errors often recur with similar structural patterns. This paper presents CORRECT, the first lightweight, training-free framework that leverages an online cache of distilled error schemata to recognize and transfer knowledge of failure structures across new requests. This cache-based reuse allows LLMs to perform targeted error localization at inference time, avoiding the need for expensive retraining while adapting to dynamic MAS deployments in subseconds. To support rigorous study in this domain, we also introduce CORRECT-Error, a large-scale dataset of over 2,000 annotated trajectories collected through a novel error-injection pipeline guided by real-world distributions, and further validated through human evaluation to ensure alignment with natural failure patterns. Experiments across seven diverse MAS applications show that CORRECT improves step-level error localization up to 19.8% over existing advances while at near-zero overhead, substantially narrowing the gap between automated and human-level error recognition.

We study learning multi-task, multi-agent policies for cooperative, temporal objectives, under centralized training, decentralized execution. In this setting, using automata to represent tasks assigned to agents enables breaking down a team-level objective into simpler, smaller sub-tasks. However, existing approaches remain sample-inefficient and are limited to the single-task case, requiring retraining policies for each new task. In this work, we present Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning (ACC-MARL), a framework for learning task-conditioned, decentralized team policies. We identify challenges to the feasibility of ACC-MARL, propose solutions, and prove that our approach is optimal. We further show that learned value functions can be used to assign tasks optimally at test time. Experiments demonstrate emergent task-aware, multi-step coordination among agents, such as pressing a button to unlock a door, holding the door, and short-circuiting tasks.

While Visual Multi-Agent Systems (VMAS) promise to enhance comprehensive abilities through inter-agent collaboration, empirical evidence reveals a counter-intuitive "scaling wall": increasing agent turns often degrades performance while exponentially inflating token costs. We attribute this failure to the information bottleneck inherent in text-centric communication, where converting perceptual and thinking trajectories into discrete natural language inevitably induces semantic loss. To this end, we propose L$^{2}$-VMAS, a novel model-agnostic framework that enables inter-agent collaboration with dual latent memories. Based on such a design, we decouple the perception and thinking while dynamically synthesizing dual latent memories. Additionally, we introduce an entropy-driven proactive triggering that replaces passive information transmission with efficient, on-demand memory access. Extensive experiments among backbones, sizes, and multi-agent structures demonstrate that our method effectively breaks the "scaling wall" with superb scalability, improving average accuracy by 2.7-5.4% while reducing total token usage by 21.3-44.8%. The codes will be publicly released.