ICML 2026 Papers

While multi-agent systems (MAS) promise elevated intelligence through coordination of agents, current approaches to automatic MAS design under-deliver. Such shortcomings stem from two key factors: (1) methodological complexity – agent orchestration is performed using sequential, code-level execution that limits global system-level holistic reasoning and scales poorly with agent complexity – and (2) efficacy uncertainty – MAS are deployed without understanding if there are tangible benefits compared to single-agent systems (SAS). We propose MASOrchestra, a training-time framework that formulates MAS orchestration as a function-calling reinforcement learning problem with holistic orchestration, generating an entire MAS at once. In MAS-Orchestra, complex, goal-oriented subagents are abstracted as callable functions, enabling global reasoning over system structure while hiding internal execution details. To rigorously study when and why MAS are beneficial, we introduce MASBENCH, a controlled benchmark that characterizes tasks along five axes: Depth, Horizon, Breadth, Parallel, and Robustness. Our analysis reveals that MAS gains depend critically on task structure, verification protocols, and the capabilities of both orchestrator and subagents, rather than holding universally. Guided by these insights, MAS-Orchestra achieves consistent improvements on public benchmarks including mathematical reasoning, multi-hop QA, and search-based QA, while achieving more than 10× efficiency over strong baselines. Together, MAS-Orchestra and MASBENCH enable better training and understanding of MAS in the pursuit of multi-agent intelligence.

The generation of Register-Transfer Level (RTL) code is a crucial yet labor-intensive step in digital hardware design, traditionally requiring engineers to manually translate complex specifications into thousands of lines of synthesizable Hardware Description Language (HDL) code. While Large Language Models (LLMs) have shown promise in automating this process, existing approaches—including fine-tuned domain-specific models and advanced agent-based systems—struggle to scale to industrial IP-level design tasks. We identify three key challenges: (1) handling long, highly detailed documents, where critical interface constraints become buried in unrelated submodule descriptions; (2) generating long RTL code, where both syntactic and semantic correctness degrade sharply with increasing output length; and (3) navigating the complex debugging cycles required for functional verification through simulation and waveform analysis. To overcome these challenges, we propose \textit{ChipV-RTL}, a multi-agent framework that leverages \textit{information locality} in modular hardware design. ChipV-RTL decomposes the long-document to long-code generation problem into a set of short-document, short-code tasks, enabling scalable generation and debugging. Specifically, ChipV-RTL integrates hierarchical document partitioning, task planning, localized code generation, interface-consistent merging, and AST-guided locality-aware debugging. Experiments on \textsc{RealBench}, an IP-level Verilog generation benchmark, demonstrate that ChipV-RTL substantially outperforms state-of-the-art (SOTA) LLMs and agents, achieving a pass rate of 45.0\% compared to 21.6\%. Code, project page are available at: \url{https://iprc-dip.github.io/ChipV-RTL/}.

Reinforcement Learning (RL) with Group Relative Policy Optimization (GRPO) shows great promise for enhancing LLM reasoning, but remains challenged by sparse and unstable rewards in long-horizon tasks. Existing approaches to reward shaping struggle to balance semantic expressiveness, reliability, and computational efficiency: heuristic rules lack flexibility, while LLM-as-a-Judge incurs high computational cost and suffer from inconsistent and misaligned scoring signals in long-context settings. To address these challenges, we introduce GLARE, a neuro-symbolic reward framework that decouples semantic abstraction from credit assignment. Specifically, to leverage semantic understanding while preserving symbolic determinism, we first extract and symbolize trajectory events into a discrete representation. These events are then translated into Linear Temporal Logic (LTL) formulas, which are compiled into deterministic automata that track the agent's progress via state transitions. This mechanism yields dense and consistent reward signals, avoiding unstable direct scoring while significantly reducing computational cost. Empirical results on ALFWorld show that GLARE outperforms GRPO by 12.1\% in success rate, while achieving an 8.1\% improvement over conventional LLM-based judges using only 15\% of their computational cost.

We introduce TFRBench, the first benchmark designed to evaluate the reasoning capabilities of forecasting systems. Traditionally, time-series forecasting has been evaluated solely on numerical accuracy, treating foundation models as "black boxes." Unlike existing benchmarks, TFRBench provides a protocol for evaluating the reasoning generated by forecasting systems--specifically their analysis of cross-channel dependencies, trends, and external events. To enable this, we propose a systematic multi-agent framework that utilizes an iterative verification loop to synthesize numerically grounded reasoning traces. Spanning ten datasets across five domains, our evaluation confirms that this reasoning is causally effective; useful for evaluation; and prompting LLMs with our generated traces significantly improves forecasting accuracy compared to direct numerical prediction (e.g., avg. $\sim40.2$% $\rightarrow$ $\sim56.6$%), validating the quality of our reasoning. Conversely, benchmarking experiments reveal that off-the-shelf LLMs consistently struggle with both reasoning (lower LLM-as-a-Judge scores) and numerical forecasting, frequently failing to capture domain-specific dynamics. TFRBench thus establishes a new standard for interpretable, reasoning-based evaluation in time-series forecasting. Our benchmark is available at: https://tfrbench.github.io

It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive games such as the prisoner's dilemma and public goods settings. Indeed, our experiments show that recent models---with or without reasoning enabled---consistently defect in single-shot social dilemmas. To tackle this safety concern, we present the first comparative study of game-theoretic mechanisms designed to enable cooperative outcomes between rational agents _in equilibrium_. Across four social dilemmas testing distinct components of robust cooperation, we evaluate four families of mechanisms: (1) repeating the game for many rounds, (2) reputation systems, (3) third-party mediators to delegate decision making to, and (4) contract agreements for outcome-conditional payments between players. Among our findings, we establish that contracting and mediation are most effective in achieving cooperative outcomes between capable LLM models, and that repetition-induced cooperation deteriorates drastically when co-players vary. Moreover, we demonstrate that the mechanisms become _more effective_ under evolutionary pressures to maximize individual payoffs.

Automated methods for discovering mechanistic simulator models from observational data offer a promising path toward accelerating scientific progress. Such methods often take the form of agentic-style iterative workflows that repeatedly propose and revise candidate models by imitating human discovery processes. However, existing LLM-based approaches typically implement such workflows via hand-crafted heuristic procedures, without an explicit probabilistic formulation. We recast model discovery as probabilistic inference, i.e., as sampling from an unknown distribution over mechanistic models capable of explaining the data. This perspective provides a unified way to reason about model proposal, refinement, and selection within a single inference framework. As a concrete instantiation of this view, we introduce ModelSMC, an algorithm based on Sequential Monte Carlo sampling. ModelSMC represents candidate models as particles which are iteratively proposed and refined by an LLM, and weighted using likelihood-based criteria. Experiments on real-world scientific systems illustrate that this formulation discovers models with interpretable mechanisms and improves posterior predictive checks. More broadly, this perspective provides a probabilistic lens for understanding and developing LLM-based approaches to model discovery.

Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) have become a promising paradigm for solving workflow-structured tasks through expert collaboration. However, the data required for such collaboration are often distributed across organizations and cannot be centrally pooled due to privacy, intellectual property, and compliance constraints. Federated Learning preserves data locality, but existing federated paradigms typically treat clients as independent and fail to model workflow dependencies that are crucial for coherent multi-stage collaboration. We introduce **FedWave**, a federated and workflow-aware framework that enables LLM-based experts to solve sequential tasks under data-locality constraints. FedWave combines a *Value Chain Layer* to model inter-stage dependencies, federated LoRA adaptation to preserve role-specific expertise, a shared *Mixture-of-Experts (MoE)* router for input-conditioned expert fusion, and a *Direct Preference Optimization (DPO)* stage based on router-induced preferences. Experiments across workflow datasets and LLM backbones show that FedWave outperforms federated baselines and remains competitive with centralized multi-agent systems while preserving data locality.

Constitutional AI has focused on single-model alignment using fixed principles. However, multi-agent systems create novel alignment challenges through emergent social dynamics. We present Constitutional Evolution, a framework for automatically discovering behavioral norms in multi-agent LLM systems. Using a grid-world simulation with survival pressure, we study the tension between individual and collective welfare, quantified via a Societal Stability Score $\mathcal{S} \in [0,1]$ that combines productivity, survival, and conflict metrics. Adversarial constitutions lead to societal collapse ($\mathcal{S}=0$), while vague prosocial principles (''be helpful, harmless, honest'') produce inconsistent coordination ($\mathcal{S}=0.249$). Even constitutions designed by Claude 4.5 Opus with explicit knowledge of the objective achieve only moderate performance ($\mathcal{S}=0.332$). Using LLM-driven genetic programming with multi-island evolution, we evolve constitutions maximizing social welfare without explicit guidance toward cooperation. The evolved constitution $\mathcal{C}^*$ achieves $\mathcal{S}=0.556\pm0.008$ (123\% higher than human-designed baselines, $N=10$), eliminates conflict, and discovers that minimizing communication (0.9\% vs 62.2\% social actions) outperforms verbose coordination. Our interpretable rules demonstrate that cooperative norms can be discovered rather than prescribed.

We introduce BioAgent Bench, an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks. The suite consists of manually curated end-to-end tasks (e.g., RNA-seq, variant calling, metagenomics) accompanied by task-specific prompts and concrete output artifacts to support automated assessment. We evaluate frontier closed- and open-weight models across multiple agent harnesses, and use an LLM-based grader to score pipeline progress and outcome validity. We find that agents based on frontier LLMs can complete multi-step bioinformatics pipelines without elaborate custom scaffolding, often producing the requested final artifacts reliably. However, robustness tests reveal failure modes under controlled perturbations (corrupted inputs, decoy files, and prompt bloat), indicating that correct high-level pipeline construction does not guarantee reliable step-level reasoning. Finally, bioinformatics workflows often involve sensitive patient data or unpublished intellectual property, thereby making the use of cost-effective yet reliable local agents an imperative. Therefore, by releasing the code and the complementary resources comprising our suite, we aim to accelerate the development of such privacy-preserving agents.

Large language model (LLM)-driven multi-agent systems typically require multiple model invocations and complex coordination during inference, and their execution strategies directly affect system accuracy, latency, and computational cost. Parallel execution provides a means to improve inference-time efficiency. From the perspective of inference-time execution, this paper models parallelism in multi-agent systems as two distinct levels of decision processes: Replica Parallelism, which explores multiple complete solution paths at the task level, and Structural Parallelism, which enables concurrent execution within a single solution path through task decomposition. However, the roles of different forms of parallelism and their interrelationships still lack systematic study in terms of unified organization and coordination. We therefore propose TIPEX, a controllable execution framework that unifies these two levels of parallelism and coordinates their roles within the inference process under a unified execution semantics while supporting systematic combinations and analyses of different parallel strategies and parameter configurations. Systematic experiments on the GAIA benchmark demonstrate that inference-time parallelism can significantly improve accuracy and reduce end-to-end latency at the cost of increased token consumption. Further analysis shows that Replica and Structural Parallelism exhibit complementary effects across task complexities, with tasks of intermediate difficulty benefiting most from their coordination, while overly aggressive parallel strategies do not necessarily yield better performance.

The design of Analog and Mixed-Signal (AMS) integrated circuits remains heavily reliant on expert knowledge, with transistor sizing a major bottleneck due to nonlinear behavior, high-dimensional design spaces, and strict performance constraints. Existing Electronic Design Automation (EDA) methods typically frame sizing as static black-box optimization, resulting in inefficient and less robust solutions. Although Large Language Models (LLMs) exhibit strong reasoning abilities, they are not suited for precise numerical optimization in AMS sizing. To address this gap, we propose \textsc{AutoSizer}, a reflective LLM-driven meta-optimization framework that unifies circuit understanding, adaptive search-space construction, and optimization orchestration in a closed loop. It employs a two-loop optimization framework, with an inner loop for circuit sizing and an outer loop that analyzes optimization dynamics and constraints to iteratively refine the search space from simulation feedback. We further introduce \textsc{AMS-SizingBench}, an open benchmark comprising 24 diverse AMS circuits in SKY130 CMOS technology, designed to evaluate adaptive optimization policies under realistic simulator-based constraints. \textsc{AutoSizer} experimentally achieves higher solution quality, faster convergence, and higher success rate across varying circuit difficulties, outperforming both traditional optimization methods and existing LLM-based agents.

When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In contrast, in real use these agents solve more various and complex tasks that involve other skills such as exploring codebases, testing software, and designing architecture. In this paper, we first characterize some transferable skills that are shared across diverse tasks by decomposing trajectories into fine-grained components, and derive a set of principles for designing auxiliary training tasks to teach language models these skills. Guided by these principles, we propose a training environment, Hybrid-Gym, consisting of a set of scalable synthetic tasks, such as function localization and dependency search. Experiments show that agents trained on our synthetic tasks effectively generalize to diverse real-world tasks that are not present in training, improving a base model by 25.4% absolute gain on SWE-Bench Verified, 7.9% on SWT-Bench Verified, and 5.1% on Commit-0 Lite. Hybrid-Gym also complements datasets built for the downstream tasks (e.g., improving SWE-Play by 4.9\% on SWT-Bench Verified). We provide the code at https://github.com/Hybrid-Gym/Hybrid-Gym.

Optimizing complex systems, ranging from LLM prompts to multi-turn agents, traditionally requires labor-intensive manual iteration. We formalize this as a stochastic generative optimization problem where a language model acts as the optimizer, guided by numerical and text feedback to discover the best system. We introduce **P**rioritized **O**ptimization with **L**ocal **C**ontextual **A**ggregation (POLCA), a scalable framework designed to handle stochasticity in optimization—such as noisy feedback, sampled minibatches, and stochastic system behaviors—while effectively managing the unconstrained expansion of the solution space. POLCA maintains a priority queue to enable exploration–exploitation, tracking candidate solutions and their evaluation histories. To enhance efficiency, we integrate an $\varepsilon$-Net mechanism to maintain parameter diversity and an LLM Summarizer to perform meta-learning across historical trials. We theoretically prove that POLCA converges to near-optimal candidate solutions under stochasticity. We evaluate our framework on diverse benchmarks, including $\tau$-bench, HotpotQA, VeriBench, and KernelBench. Experimental results demonstrate that POLCA achieves robust, sample- and time-efficient performance, consistently outperforming state-of-the-art algorithms in both deterministic and stochastic problems. The codebase for this work is publicly available at https://github.com/rlx-lab/POLCA.

Full-duplex voice agents—systems that listen and speak simultaneously—are rapidly moving from research to production. However, existing evaluations address conversational dynamics and task completion in isolation. We introduce τ-Voice, a benchmark for evaluating voice agents on grounded tasks with real-world complexity: agents must navigate complex multi-turn conversations, adhere to domain policies, and interact with the environment. The framework extends τ²-bench into a novel voice agent benchmark combining verifiable completion of complex grounded tasks, full-duplex interaction, and realistic audio—enabling direct comparison between voice and text performance. A controllable and realistic voice user simulator provides diverse accents, realistic audio environments, and rich turn-taking dynamics; by decoupling simulation from wall-clock time, the user simulator can use the most capable LLM without real-time constraints. We evaluate task completion (pass@1) and voice interaction quality across 278 tasks: while GPT-5 (reasoning) achieves 85%, voice agents reach only 31–51% under clean conditions and 26–38% under realistic conditions with noise and diverse accents—retaining only 30–45% of text capability; qualitative analysis confirms 79–90% of failures stem from agent behavior, suggesting that observed failures primarily reflect agent behavior under our evaluation setup. τ-Voice provides a reproducible testbed for measuring progress toward voice agents that are natural, conversational, and reliable.

Reliable evaluation of large language model (LLM) agents depends critically on benchmark validity, yet modern agent benchmarks often contain hidden flaws arising from interactions among user instructions, environments, tools, ground-truth trajectories, and evaluation protocols. These flaws confound model errors with benchmark artifacts and undermine leaderboard-based comparisons. We propose **COBA** (**CO**mponent-based **B**enchmark **A**uditing), an automated pipeline for diagnosing and filtering validity issues in agent benchmarks. COBA decomposes agent tasks into four standardized components—User, Environment, Ground Truth, and Evaluation—and operationalizes a component-level issue taxonomy using hybrid rule-based detectors and taxonomy-guided LLM evaluation. Across six widely used agent benchmarks, COBA achieves strong alignment with expert judgments, with F1 scores between 0.791 and 0.874. It complements manual verification of $\tau^2$-bench by identifying issues missed due to benchmark complexity, and generalizes to previously unseen benchmarks with minimal adaptation. Our analysis shows that benchmark flaws are widespread and materially affect evaluation outcomes, demonstrating that component-based auditing provides a scalable foundation for more reliable and interpretable agent evaluation. We release AgentSuite, a unified benchmark-running platform that includes the COBA auditing pipeline and audited benchmark variants: https://github.com/Agent-Suite/AgentSuite.

Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents. Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning. However, these approaches typically operate at a coarse instance granularity, treating the entire problem-solving episode as the atomic unit of storage and retrieval. We empirically demonstrate that instance-level memory suffers from a fundamental granularity mismatch, resulting in misguided retrieval when tasks with similar surface descriptions require distinct reasoning logic at specific stages. To address this, we propose Structurally Aligned Subtask-Level Memory, a method that aligns memory storage, retrieval, and updating with the agent’s functional decomposition. Extensive experiments on SWE-bench Verified demonstrate that our method consistently outperforms both vanilla agents and strong instance-level memory baselines across diverse backbones, improving mean Pass@1 over the vanilla agent by +4.7 pp on average (e.g., +6.8 pp on Gemini 2.5 Pro). Performance gains grow with more interaction steps, showing that leveraging past experience benefits long-horizon reasoning in complex software engineering tasks.

Multimodal reasoning for ultra-high-resolution (UHR) remote sensing (RS) is usually bottlenecked by visual evidence acquisition: the model necessities localizing tiny task-relevant regions in massive pixel spaces. While Agentic Reinforcement Learning with Verifiable Rewards (RLVR) using zoom-in tools offers a path forward, we find that standard reinforcement learning struggles to navigate these vast visual spaces without structured domain priors. In this paper, we investigate the interplay between post-training paradigms: comparing Cold-start Supervised Fine-Tuning (SFT), RLVR, and Agentic RLVR on the UHR RS benchmark. Our controlled studies yield a counter-intuitive finding: high-quality Earth-science text-only QA is a primary driver of UHR visual reasoning gains. Despite lacking images, domain-specific text injects the concepts, mechanistic explanations, and decision rules necessary to guide visual evidence retrieval. Based on this, we propose a staged knowledge injection recipe: (1) cold-starting with scalable, knowledge-graph-verified Earth-science text QA to instill reasoning structures; and (2) "pre-warming'' on the same hard UHR image–text examples during SFT to stabilize and amplify subsequent tool-based RL. This approach achieves a 60.04\% Pass@1 on XLRS-Bench, significantly outperforming larger general-purpose models (e.g., GPT-5.2, Gemini 3.0 Pro, Intern-S1) and establishing a new state-of-the-art. We provide both the automated data pipeline and the rigorous ablation studies that validate this "Text-Before-Vision'' paradigm. Datasets and code will be released.

We introduce Debate2Create (D2C), a multi-agent LLM framework that formulates robot co-design as structured, iterative debate grounded in physics-based evaluation. A design agent and control agent engage in a thesis-antithesis-synthesis loop, while criterion-specific LLM judges provide multi-objective feedback to steer exploration. Across five MuJoCo locomotion benchmarks, D2C achieves the highest default-normalized score among the evaluated LLM-based and black-box baselines, with gains up to 3.2x on Ant and nearly 9x on Swimmer. Iterative debate yields 18-35% gains over compute-matched zero-shot generation, and D2C-generated rewards transfer to default morphologies in 4/5 tasks. These results suggest that structured, simulator-grounded multi-agent interaction is a useful mechanism for joint morphology-reward optimization under a fixed-topology, per-candidate-RL protocol. Project page: debate2create.github.io.

The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectures introduce a critical bottleneck: redundant prefill computation for shared content generated by previous agents, which significantly increases KV cache memory usage and time-to-first-token (TTFT). While various KV cache methods have been proposed to mitigate prefill redundancy, they either fail to maintain accuracy on agent-generated outputs or exhibit low reuse rates due to rigid constraints. We present RelayCaching, a training-free inference method that directly reuses decoding phase KV caches from previous agents in subsequent prefill phases. Our key insight is that KV caches for identical content are highly consistent across phases, while prefix-induced deviations are sparse and localized within a limited range of layers and token positions. By selectively recomputing KV caches at these positions, RelayCaching preserves model accuracy with minimal overhead, yielding a superior accuracy–efficiency trade-off over existing methods. Experiments on diverse collaborative LLM tasks spanning mathematical reasoning, general knowledge, and code generation demonstrate that RelayCaching achieves over $80$\% KV cache reuse, reduces TTFT by up to $4.7\times$ compared to the standard pipeline, all with negligible accuracy degradation.