NeurIPS 2026 论文列表

In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-dependent workflow construction, the lack of graph-level execution feedback, and the inability to repair errors in-loop during long-horizon construction. To address these challenges, we propose FlowSteer, a new paradigm of Agent Designing Agentic Workflows — a single agent itself end-to-end designs the workflow that a downstream executor runs. To support this paradigm, we introduce the Workflow Canvas, a novel executable graph-state environment that returns syntax-checked execution feedback for every atomic edit. Built on the canvas, we further propose Reinforced Progressive Canvas Editing, in which a lightweight policy agent issues one atomic edit per turn conditioned on real canvas feedback, and is trained end-to-end via reinforcement learning. Moreover, FlowSteer provides a plug-and-play framework that supports diverse operator libraries and interchangeable LLM backends. Experimental results on twelve datasets show that FlowSteer significantly outperforms baselines across various tasks. Our code is available at https://anonymous.4open.science/r/FlowSteer-9B2E.

Recent work has demonstrated that online reinforcement learning (RL) can substantially improve the quality and alignment of flow matching models for image and video generation. Methods such as Flow-GRPO and CPS cast the denoising process as a Markov Decision Process and apply PPO-style ratio clipping to enforce a trust region. However, we argue that *ratio clipping is structurally ill-suited for flow models*: the probability ratio between new and old policies is a noisy, single-sample estimate of the true policy divergence, leading to over-constraining in some regions of the trajectory and under-constraining in others. We propose **Flow-DPPO** (Flow Divergence Proximal Policy Optimization), which replaces ratio clipping with a divergence proximal constraint. A key observation is that the per-step policy in flow models is Gaussian, enabling *exact* and *cheap* computation of the KL divergence between old and new policies. Flow-DPPO employs an asymmetric divergence mask that blocks gradient updates only when they simultaneously move away from the trusted region and violate the divergence threshold. Experiments show that Flow-DPPO achieves higher rewards with better KL-proximal efficiency, alleviates catastrophic forgetting, promotes balanced multi-objective optimization, and enables stable multi-epoch training where ratio clipping degrades.

Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined to continuous action spaces. To address a broader range of offline RL settings, we extend flow matching to a general framework that supports discrete action spaces with multiple objectives. Specifically, we replace continuous flows with continuous-time Markov chains, trained using a Q-weighted flow matching objective. We then extend our design to multi-agent settings, mitigating the exponential growth of joint action spaces via a factorized conditional path. We theoretically show that, under idealized conditions, optimizing this objective recovers the optimal policy. Extensive experiments further demonstrate that our method performs robustly across diverse settings and benchmarks, including high-dimensional control, multi-agent games, and dynamically changing preferences over multiple objectives, while outperforming traditional offline RL methods in practical multi-modal decision-making scenarios. Our discrete framework can also be applied to continuous-control problems through action quantization, providing a flexible trade-off between representational complexity and performance.

We develop a unified framework for flow-based reinforcement learning (RL) grounded in diffusion–flow duality and establish its theoretical foundations. The frameworks enables RL for deterministic flow matching inference by introducing diffusion stochastic inference dynamics that supports exploration while admitting deterministic deployment. We show that our frameworks subsumes several existing flow-based RL methods as special cases and inspire effective now methods. Then we provide theoretical foundations for the frameworks by establishing the correctness and performance transfer guarantee. Specifically, we prove that the policies optimized under stochastic dynamics close to deterministic dynamics at deployment when the pretrained model is well-trained. Moreover, we show that the policy improvement achieved under training-time SDE inference transfers to deployment-time ODE inference. Finally, we conduct experiments to validate our theoretical results.

Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-based diffusion policies can represent complex, multimodal action distributions, they suffer from two critical limitations: their stochastic reverse processes render entropy intractable (necessitating heuristic exploration), and computing policy gradients through long denoising chains is expensive and unstable. In this work, we show that ODE-based flow matching inherently resolves these issues by enabling both simulation-free policy optimization and tractable entropy computation. Building on this, we introduce Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints (FMER). Our framework exploits this insight in three ways. First, we theoretically establish that minimizing an advantage-weighted conditional flow matching loss acts as a simulation-free surrogate for policy mirror descent. This steers the velocity field toward high-value regions while entirely avoiding backpropagation through the ODE solver. Second, we derive an analytic entropy objective that corrects for the density distortion caused by the $\tanh$ transformation (mapping an unbounded latent space to bounded actions), thereby facilitating principled maximum-entropy optimization. Finally, we dynamically tune the mirror descent temperature based on the effective sample size to enforce a robust trust region during training. Empirical evaluations demonstrate that FMER achieves superior performance on the challenging sparse-reward FrankaKitchen environment, while maintaining competitive results across standard dense-reward MuJoCo benchmarks. Code is available at \url{https://anonymous.4open.science/r/submission-25E2/}.

Reliable hypothesis testing is the foundation of many empirical scientific claims. Large language model (LLM) agents are increasingly used to automate this process, as they can inspect datasets, generate code, and produce analyses end-to-end. However, we show that they frequently make subtle inferential errors that lead to incorrect conclusions despite correctly executed analyses. Existing benchmarks fail to capture this failure mode, as they rarely assess whether a reported p-value is statistically valid given the assumptions underlying the data. We address this gap by building P-Bench, a benchmark comprising 425 open-ended, realistic hypothesis-testing tasks spanning economics, biology, and medicine. Each task requires an agent to select a statistical method, compute a p-value, and draw a conclusion given only a scientific hypothesis and a dataset. We further introduce Fisher-R1, an open-weight LLM agent trained for rigorous hypothesis testing using synthetic tasks and reinforcement learning. On P-Bench, Fisher-R1-14B substantially improves over its backbone and outperforms strong proprietary and open-source baselines, including GPT-5.4 and DeepSeek-V4-Pro, achieving a 21% average relative improvement in single-trial success over DeepSeek-V4-Pro, with gains up to 26% on the most challenging tasks. Our results demonstrate that current LLM agents lack reliable statistical reasoning for hypothesis testing and that reinforcement learning on tasks with verified statistical reward substantially improves reliability.

Modern models can have high average accuracy and benign loss tails while remaining fragile on rare subpopulations. We identify an information-geometric mechanism: after nuisance projection, the task direction can become locally nonidentifiable even when loss and raw Fisher look well behaved. Fisher-Glass certifies this failure by applying CVaR to inverse nuisance-projected task information. We prove a loss--information separation theorem and show that, under a boundary-mass condition, the hidden-environment tail of inverse projected Fisher controls robust classification sample complexity. We then derive stable ridge certificates and repair principles: reserves lift Fisher-null tails, portfolios increase collapse codimension, and tail-transverse influence selects counterfactual repairs by combining Fisher-Glass directionality with loss leverage. Synthetic experiments validate the theory; WILDS/Waterbirds diagnostics show that weakest identifiability need not mean lowest accuracy; and Waterbirds training plus counterfactual repair show that Fisher-Glass controls an identifiability axis complementary to loss.

We study the problem of average reward Multi-Agent Reinforcement Learning (MARL) where agents interact within a network. Each agent in the network conducts local updates with information within its $k$-hop neighborhood and collaboratively maximizes the overall reward of the entire network. We first provide impossibility results in achieving convergence to the global optimal joint policies in our setting. These impossibility results highlight the challenges of decentralized learning with local information in multi-agent systems, namely the issues of multiagency, where each agent independently optimizes its policy, and partial observability, where agents have limited visibility into the global state. Given these challenges which indicate that decentralized policy optimization can generally be certified only up to stationarity, we provide finite-sample convergence guarantees for a decentralized actor-critic algorithm with linear function approximation that converges to an approximate stationary point with small gradient norm. To overcome such impossibility results, we further show that adding fixed-state entropy regularization reshapes the objective landscape which leads to even stronger global convergence guarantees for our proposed actor-critic algorithm.

Exact optimal-decision recovery can be stronger than required when decisions are evaluated at a finite regret tolerance. This paper studies finite-resolution sufficiency under partial linear observations and bounded measurement error. A design is sufficient when every noisy observation fiber admits a single feasible decision with regret at most a prescribed tolerance for all costs in that fiber. We prove a complete finite certificate for insufficiency: an indistinguishable hard tuple of costs with no common low-regret decision. For linear-optimization regret, the required tuple size is controlled by projected cost dimension after quotienting directions that are invisible to regret. For finite cost libraries, this certificate gives exact fixed-design verification and separation. Under coordinatewise noise and a finite query library, query design is exactly set cover over hard tuples; this reduction transfers the standard set-cover greedy guarantee and hardness barrier, and supports an exact delayed-constraint method under exact verification and exact restricted-master solves. Structured cases reduce to polynomial formulations through separability, nested one-dimensional coverage, and interval incidence.

Estimating the principal eigenpair of a positive operator from stochastic evaluations gives rise to a noisy form of normalized power iteration: each step applies a sampled operator estimate and then renormalizes. We establish finite-time stochastic-approximation guarantees for this procedure, working in Hilbert's projective metric, which is well-suited to the multiplicative geometry of Perron--Frobenius eigenproblems. Our main application is risk-sensitive average-cost reinforcement learning (RL) with exponential utility. In this setting the Bellman equations are multiplicative, and value functions are characterized by nonlinear eigenvalue problems rather than additive fixed points. We cast both policy evaluation and control in this framework, obtaining risk-sensitive TD- and Q-learning algorithms that learn from a single Markovian trajectory. Under explicit positivity, mixing, and linear function approximation assumptions, we prove finite-time bounds on the recovered eigenvector and eigenvalue with $\tilde{O}(\epsilon^{-2})$ sample complexity up to problem-dependent constants. The results cover both tabular and linear function approximation regimes, and through the duality between exponential utility and KL-robust control yield finite-time guarantees for KL-robust average-cost RL as well.

Introducing new capabilities to frontier models has long been the goal for posttraining, which relies predominantly on supervised finetuning (SFT) and reinforcement learning (RL) to achieve this. Prevailing wisdom dictates that on-policy RL enables strong generalization on new tasks without losing existing capabilities, while SFT is prone to weak generalization and forgetting. At the same time, SFT enables learning from inherently off-policy expert data, whereas RL must rely on a model's ability to generate positive signal on a new task. In our work, we seek to bridge the strength of on-policy learning with the information signal of off-policy expert traces. To this end, we introduce a Markov chain Monte Carlo (MCMC) sampling algorithm that transforms off-policy traces into more on-policy ones given a reference model for finetuning. Across tasks like scientific skill acquisition, mathematical reasoning, and fact learning, we demonstrate that simple SFT on these boosted off-policy traces can generalize better and forget less than on-policy counterparts. More generally, our approach outlines a principled methodology for model-specific data refinement, suggesting broader utility as a plug-and-play component throughout the post-training pipeline.

With the rapid progress of Multimodal Large Language Models (MLLMs), unified MLLMs that jointly perform image understanding and generation have advanced significantly. However, despite the inherent reasoning capabilities of unified MLLMs for self-reflection and self-refinement, their use in text-to-image generation remains largely underexplored. Meanwhile, existing multimodal reasoning–based image generation methods mostly rely on prompt augmentation or holistic image–text alignment judgments, without fine-grained reflection and refinement of detailed prompt attributes, leading to limited fine-grained control. To address this limitation, we propose FiRe, a Fine-grained Multimodal Reasoning method for enhanced image generation by MLLM. In specific, FiRe performs a fine-grained multi-step reasoning by first decomposing the prompt into key visual requirements and then self-judging their satisfaction in the generated image, followed by localized refinement according to self-generated precise feedback. In addition, to further strengthen the MLLM's multimodal reasoning ability, we introduce FiRe-GRPO, a reinforcement learning method tailored to FiRe. Since standard Group Relative Policy Optimization (GRPO) suffers from sparse, outcome-based rewards in multi-step reasoning, we formulate our reasoning process as a step-level decision-making problem, design step-specific rewards, and compute step-level advantages for granular credit assignment within GRPO. Extensive experiments demonstrate that FiRe consistently outperforms competitive text-to-image baselines, including existing reasoning-based methods, with particularly substantial gains on compositional text-to-image benchmarks.

Fairness has emerged as a central consideration in machine learning, motivating the study of fair range $k$-supplier clustering as a fundamental problem that focuses fairness on the selected centers. Given a set of suppliers and clients, where each supplier may belong to one or more demographic or functional groups, the objective is to select $k$ suppliers that minimize the maximum client-to-center distance while ensuring that the number of selected suppliers from each group satisfies prescribed lower and upper bounds. For disjoint supplier groups, we develop a polynomial-time $3$-approximation algorithm in the offline setting and a $(3+\epsilon)$-approximation algorithm in the streaming setting. We further consider overlapping supplier groups and show that this generalization admits a parameterized $3$-approximation algorithm whose runtime is exponential in the number of clusters. Finally, experiments on both synthetic and real-world datasets demonstrate that our algorithms achieve significantly better clustering quality and runtime efficiency in comparison with state-of-the-art methods.

Maximum entropy reinforcement learning (MaxEnt-RL) enables robust exploration, yet practical implementations often restrict policies to simple Gaussians. While recent approaches incorporate expressive generative policies via importance-weighted supervised learning, they are prone to importance weight collapse, which limits their scalability in high-dimensional action spaces. Our key insight is to mitigate this limitation by localizing the sampling region, avoiding the weight degeneracy induced by importance sampling over the entire action space. To instantiate this insight, we introduce **FLAG** (**F**low policy with **L**atent-**A**ugmented **G**uidance). FLAG augments the state space with a flow latent variable and optimizes a provably consistent proxy MaxEnt-RL objective. We empirically demonstrate that FLAG enables expressive policy optimization with limited importance samples and scales to high-dimensional control tasks. Furthermore, FLAG achieves state-of-the-art performance across challenging benchmarks.

Memorization in large language models has been studied almost exclusively through prefix-conditioned extraction, a natural choice for autoregressive models. However, diffusion language models (DLMs) can denoise masked tokens at arbitrary positions. Thus, prefix-only probing reveals only one facet of memorization in DLMs and significantly underestimates the risk of training-data extraction. In order to realistically model extractability of training data in DLMs, we introduce infilling extraction, a data-extraction protocol parameterized by an arbitrary binary mask that subsumes prefix-only probing and accounts for the bidirectional inductive bias of DLMs. Instantiating it on LLaDA-8B and Dream-7B across five extraction modes, three training pipelines, and three corpora covering verbatim and partial leakage, we find that mask geometry governs extractability: edge-conditioned masks extract up to three times more verbatim sequences than prefix-conditioned ones, and bidirectional access opens channels inaccessible in autoregressive models. In particular, we show that a realistic adversary with access to training data where personally identifiable information has been redacted, can even achieve higher recall on extracting redacted email addresses from DLMs than from scale-matched autoregressive models. Tunable parameters for decoding measurably affect extraction performance, while a follow-up supervised finetuning stage does not eliminate the prior memorization.

The asymptotic behaviour of Monte Carlo Exploring Starts (MCES) is a long-standing open question in reinforcement learning, even in the tabular setting. We investigated the convergence properties of tabular MCES by constructing examples in which the algorithm converges to suboptimal solutions. This paper presents new counterexamples for both initial-visit and first-visit MCES and gives a convergence-restoring modification for the initial-visit case. We show that stable suboptimal solutions may exist for initial-visit MCES with sample-average updates even when greedy actions are updated more often than non-greedy actions on average. However, by scaling learning rates inversely to update frequencies on a state-by-state basis, convergence to optimality is guaranteed. Unlike previous uniformisation methods, this modification is applicable to large-scale problems that require approximating the estimated value function. We then extend the example to show that sample-average first-visit MCES may also converge to suboptimal solutions. This largely settles a fundamental open problem and shows that exploring starts alone do not guarantee convergence to optimality. More broadly, these results highlight that convergence depends critically on the relative size and frequency of updates applied to different actions, making the choice of learning rates and the balance between exploration and exploitation central to the analysis of MCES and the implementation of scalable Monte Carlo control methods.

Standard In-Context Reinforcement Learning (ICRL) typically assumes stationary dynamics within an interaction history, a restriction that limits its real-world applicability. We formalize Lifelong ICRL, a more realistic paradigm in which agents must continuously adapt to diverse non-stationary dynamics, ranging from abrupt random shifts to structured temporal drifts within a single lifetime. To probe the adaptation limits of this setting, we conduct a large-scale empirical study across non-stationary environments that span discrete symbolic reasoning and continuous physics-based control. We systematically investigate three core dimensions governing adaptation: (i) Training Regimes, comparing the generalization boundaries of domain randomization, stationary training, non-stationary training, and their staged combinatorial strategies; (ii) Model Architectures, evaluating modern sequence models, including Linear Attention and hybrid designs; and (iii) Impact of Scale, analyzing the relative contributions of interaction scale and model capacity. Our results reveal how these factors jointly shape robust in-context adaptation under unknown dynamics, yielding actionable insights for the design of generalist agents.

While federated reinforcement learning has traditionally guaranteed high efficiency in homogeneous environments, collaboration is often hindered when agents possess distinct environments and goals. In this paper, we flip this paradigm, framing reward heterogeneity not as a hurdle to consensus, but as a structural asset that catalyzes exploration. We first propose Personalized Federated Upper Confidence Bound Value Iteration (PF-UCBVI), which achieves optimal linear speedup by decoupling shared dynamics from personalized objectives. To eliminate the risks of explicit exploration, we then introduce Personalized Federated Exploration-Free Value Iteration (PF-EFVI), a purely greedy algorithm that leverages reward diversity to ensure state-action coverage. We prove that PF-EFVI attains logarithmic regret without explicit exploration bonuses under sufficient reward diversity. Our results show that agent disagreement is a vital resource that shifts the exploration burden from temporal complexity to spatial diversity, enabling safe and efficient collective learning.

Reinforcement learning (RL) agents face a continuous trade-off between exploiting known strategies and exploring novel states to obtain higher rewards. While exploration is often undirected, it can also be guided by intrinsic signals such as novelty or uncertainty. However, combining these signals with task rewards is challenging, as they can sometimes drive the agent away from optimal trajectories and reduce final performance. We find that this degradation arises from a structural occupancy conflict: as the policy improves, exploration signals naturally begin to anti-correlate with task advantages. In this work, we introduce Kantorovich Dual Shaping (KDS), a framework that resolves this conflict through constrained policy-space optimization. KDS formulates exploration as an Optimal Transport problem and applies the Sinkhorn-Knopp algorithm on the empirical batch manifold to reweight intrinsic rewards in a geometry-aware, point-by-point manner. When combined with standard RL objectives, it acts as a spatial filter that suppresses exploration in conflicting regions while enhancing it elsewhere. We evaluate this general approach across multiple off-policy and on-policy algorithms, achieving stable exploration that consistently avoids task degradation in complex continuous control environments.