论文检索

Deep Learning · Large Language Models

Jingyuan Ma, Zheng Li, Rui Li, Siyao Song, Ying Zeng, MINGHAO LI, Zhifang Sui

Large language models still struggle to reliably answer questions grounded in real-world files like spreadsheets and slides, where evidence is scattered across irregular layouts and heterogeneous formats. We address this by formalizing File Reasoning, a setting where agents must interact directly with unprocessed files (XLSX, PDF, DOCX, PPTX) within a persistent sandbox. To support this, we introduce a unified data pipeline and release a high-difficulty benchmark of over 400 verifiable tasks that preserve native file structure. Furthermore, we propose a reinforcement learning framework grounded in stateful file execution. We train and release **FIRE** (**F**ile **I**nteractive **R**easoning **E**xpert), a family of models that learn to optimize long-horizon planning using genuine execution feedback from the environment. Unlike stateless tool-use methods, our approach enables agents to recover from errors and adapt to structural ambiguities. Empirical results show that Qwen3-32B-FIRE achieves the strongest performance among open-source models under identical execution constraints.

Deep Learning · Large Language Models

Mickel Liu, Liwei Jiang, Yancheng Liang, Simon Du, Yejin Choi, Tim Althoff, Natasha Jaques

Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders patch exposed vulnerabilities. This sequential setup leads to attackers overfitting obsolete exploits while defenders perpetually lag behind emerging threats. To address this, we introduce Self-RedTeam, the first fully online self-play multi-agent reinforcement learning (MARL) algorithm that continuously co-evolves attacker and defender for robust safety alignment. A single policy self-plays as both attacker and defender, generating adversarial prompts and defending against them, with a reward model adjudicating outcomes. Each role uses hidden chain-of-thought for strategic planning. Grounded in two-player zero-sum game theory, we establish a theoretical safety guarantee: if the game converges to Nash Equilibrium, the defender produces safe responses against any adversarial input. Empirically, Self-RedTeam generalizes across five models from the Llama and Qwen families, uncovering more diverse attacks (+17.80% SBERT) and improving safety of RLHF-trained models by up to 95% across 14 benchmarks. Our work motivates a shift from reactive patching to proactive co-evolution, enabling LLM safety self-improvement via online self-play MARL.

Deep Learning · Large Language Models

Yihang Yao, Zhepeng Cen, Haohong Lin, Shiqi Liu, Zuxin Liu, Jiacheng Zhu, Zhang-Wei Hong, Laixi Shi, Ding Zhao

Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric applications. Agentic reinforcement learning (RL) has recently emerged as a promising solution for training such agents in multi-turn settings, allowing interaction strategies to be learned from feedback. However, existing pipelines face a critical challenge in balancing task performance with user engagement, as passive agents can not efficiently adapt to users' intentions while overuse of human feedback reduces their satisfaction. To address this trade-off, we propose BAO, an agentic RL framework that combines behavior enhancement to enrich proactive reasoning and information-gathering capabilities with behavior regularization to suppress inefficient or redundant interactions and align agent behavior with user expectations. We evaluate BAO on multiple tasks from the UserRL benchmark suite, and demonstrate that it substantially outperforms RL baselines under controlled comparisons, while achieving comparable or even superior performance to frontier LLM agents, highlighting its effectiveness for training proactive, user-aligned LLM agents in complex multi-turn scenarios.

Reinforcement Learning · Everything Else

Zihao Wang, Muyao Li, Kaichen He, Haowei Lin, Xiaojian Ma, Anji Liu, Yitao Liang

Prevailing autonomous agents are often constrained by a single, predefined action space, which limits their generalization capabilities across diverse tasks and can introduce compounding errors through decoupled policy execution. To address these limitations, we introduce the Deep Hierarchical Agent (DeepHA), a unified architecture that operates across a mixture of heterogeneous action spaces, flexibly generating actions ranging from high-level semantic skills to low-level motor controls. We further propose a Chain-of-Action (CoA) reasoning framework, which enables the agent to use higher-level abstract actions as structured `thoughts' to guide the generation of more granular, subsequent actions. To manage the computational demands of this deep reasoning in long-horizon tasks, we develop a memory-efficient mechanism that dynamically compresses historical context and leverages Key-Value (KV) caching, reducing context length by approximately 75% without sacrificing performance. We conduct extensive evaluations on a new, large-scale benchmark of over 800 diverse Minecraft tasks. Results show that DHA significantly outperforms prior methods, establishing a new state-of-the-art and demonstrating superior generalization, particularly in complex, multi-step planning tasks. Our work presents a novel, unified framework for building more capable and efficient autonomous agents.

Reinforcement Learning · Deep RL

Youngin Kim, Ray Sun, Inho Kim, Bumsoo Park, Hyun Oh Song

Transformer-based world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A key reason is that most existing approaches treat next-frame prediction purely as a token generation problem, without explicitly modeling correspondence between tokens across time. We formulate next-frame prediction as a structured probabilistic inference problem with latent token correspondence variables, deriving a model in which each next-frame token is explained either by copying a token from the previous frame or by generating a new token. Our experiments show state-of-the-art performance on 4 challenging benchmarks. The proposed method achieves a return of 72.5% and a score of 35.6% on the Craftax-classic benchmark, significantly surpassing the previous best of 67.4% and 27.9%. We plan to release our source code on GitHub upon acceptance.

Reinforcement Learning · Planning

Yuqi Pan, Davin Choo, Haichuan Wang, Milind Tambe, Alastair van Heerden, Cheryl Johnson

We study a sequential resource allocation problem motivated by adaptive network recruitment, in which a limited budget of identical resources must be allocated over multiple rounds to individuals with stochastic referral capacity. Successful referrals endogenously generate future decision opportunities while allocating additional resources to an individual exhibits diminishing returns. We first show that the single-round allocation problem admits an exact greedy solution based on marginal survival probabilities. In the multi-round setting, the resulting Bellman recursion is intractable due to the stochastic, high-dimensional evolution of the frontier. To address this, we introduce a population-level surrogate value function that depends only on the remaining budget and frontier size. This surrogate enables an exact dynamic program via truncated probability generating functions, yielding a planning algorithm with polynomial complexity in the total budget. We further analyze robustness under model misspecification, proving a multi-round error bound that decomposes into a tight single-round frontier error and a population-level transition error. Finally, we evaluate our method on synthetic and real-world recruitment scenarios.

Reinforcement Learning · Everything Else

Yuetian Wang, Dianxi Shi, Yuanze Wang, Huanhuan Yang, Shiming Song, Chunping Qiu

Safe reinforcement learning (Safe RL) seeks to optimize long-term performance while ensuring adherence to safety constraints. However, most existing approaches address safety in a simplified manner, typically by linearly combining rewards and costs, which provides limited guidance when safety and performance interact in complex, nonlinear ways. We present USB-RL (Unsupervised Score-Balanced Reinforcement Learning), a model-based framework that learns implicit safety–performance preferences directly from experience. Our approach infers a monotone partial-order score through unsupervised pairwise comparisons of long-horizon outcomes, capturing nuanced trade-offs without relying on manually tuned cost weights. The learned score guides model-based policy optimization by dynamically balancing safety and performance, enabling flexible and adaptive multi-step planning in imagination-based control. Across diverse safety benchmarks, USB-RL achieves strong returns while substantially reducing safety violations, demonstrating stable and interpretable safety–performance trade-offs.

Theory · Reinforcement Learning and Planning

Ziyue Chu, Leonardo Stella

Multi-agent reinforcement learning (MARL) has received increasing attention for solving complex decision-making tasks. Networked MARL approaches offer a decentralized solution for parameter sharing to accelerate training via value aggregation. However, existing federated aggregations rely on convex averaging that may fail to converge to global optima and cause learning rollback in the online learning setting. In this paper, we formally characterize the learning rollback phenomenon arising from aggregating value estimates with unequal uncertainty under heterogeneous online update depths. We propose a novel adaptive global consensus (AGC) mechanism for Q-value aggregation in decentralized MARL policy evaluation, which dynamically adjusts aggregation weights based on agents’ uncertainty. We establish theoretical guarantees on accelerated convergence and bounded learning variance with empirical validations, advancing the state-of-art MARL theory.

Reinforcement Learning · Planning

Ziqing Lu, Babak Hassibi, Lifeng Lai, Weiyu Xu

Reinforcement learning usually assumes a given or sometimes even fixed environment in which an agent seeks an optimal policy to maximize its long-term discounted reward. In contrast, we consider agents that are not limited to passive adaptations: they instead have model-changing actions that actively modify the RL model of world dynamics itself. Reconfiguring the underlying transition processes can potentially increase the agents' rewards. Motivated by this setting, we introduce the multi-layer configurable time-varying Markov decision process (MCTVMDP). In an MCTVMDP, the lower-level MDP has a non-stationary transition function that is configurable through upper-level model-changing actions. The agent's objective consists of two parts: Optimize the configuration policies in the upper-level MDP and optimize the primitive action policies in the lower-level MDP to jointly improve its expected long-term reward.

Reinforcement Learning · Planning

Shenghua Wan, Xiaohai Hu, Xunlan Zhou, lei yuan, Le Gan, De-Chuan Zhan

The scalability of world models is currently bottlenecked by the scarcity of action annotations. While self-supervised latent action learning offers a potential solution, existing single-view paradigms—relying on information bottlenecks or Vector Quantization (VQ)—often conflate superficial 2D pixel displacements with the underlying physical-spatial dynamics of an action. Consequently, these methods remain highly susceptible to view-dependent noise, such as camera shake. We introduce **MuCoLA** (**Mu**lti-view **Co**nsistent **L**atent **A**ction learning), a framework that learns robust, view-invariant action representations by enforcing semantic consistency across synchronized video streams. MuCoLA utilizes a Student-Teacher network with DINO-style self-distillation to align action distributions across viewpoints, effectively filtering high-frequency visual noise while preserving motion semantics. Theoretical analysis reveals that our multi-view objective functions as a spectral filter, isolating agent dynamics from environmental nuisances. Empirically, MuCoLA significantly outperforms baselines in action regression, video reconstruction, and downstream visual control tasks. Furthermore, we demonstrate that MuCoLA exhibits favorable scaling properties with respect to model capacity and data volume, paving the way for large-scale action-free world modeling.

Reinforcement Learning · Policy Search

Álvaro Serra-Gómez, Daniel Jarne Ornia, Dhruva Tirumala, Thomas M Moerland

Effective exploration remains a key challenge in model-based reinforcement learning (MBRL), especially in high-dimensional continuous control tasks where sample efficiency is critical. Recent work addresses this by using learned policies as proposal distributions for Model-Predictive Path Integral (MPPI) planning. Early approaches update the sampling policy independently of the planner, typically via deterministic policy gradients with entropy regularization. However, since the data distribution is induced by the MPPI planner, misalignment between the policy and planner degrades value estimation and long-term performance. To address this, recent methods explicitly align the policy with the planner by minimizing KL divergence to the planner distribution or by incorporating planner-guided regularization. In this work, we unify these approaches under the Policy Optimization–Model Predictive Control (PO-MPC) framework, a family of KL-regularized MBRL methods that treat the planner’s action distribution as a prior in policy optimization. We show how existing methods emerge as special cases of this family and explore previously unstudied variants. Experiments demonstrate that these variants yield significant performance gains, advancing the state of the art in MPPI-based RL.

Applications · Robotics

Zhixuan Shen, Jiawei Du, Ziyu Guo, Han Luo, Lilan Peng, Joey Tianyi Zhou, Haonan Luo, Tianrui Li

Vision-Language Models (VLMs) have demonstrated exceptional general reasoning capabilities. However, their performance in embodied navigation remains hindered by a scarcity of aligned open-world vision and robot control data. Despite simulators providing a cost-effective alternative for data collection, the inherent reliance on photorealistic simulations often limits the transferability of learned policies. To this end, we propose \textit{\textbf{S}andbox-\textbf{A}bstracted \textbf{G}rounded \textbf{E}xperience} (\textbf{\textit{SAGE}}), a framework that enables agents to learn within a physics-grounded semantic abstraction rather than a photorealistic simulation, mimicking the human capacity for mental simulation where plans are rehearsed in simplified physics abstractions before execution. \textit{SAGE} system operates via three synergistic phases: (1) \textit{Genesis}: constructing diverse, physics-constrained semantic environments to bootstrap experience; (2) \textit{Evolution}: distilling experiences through Reinforcement Learning (RL), utilizing a novel asymmetric adaptive clipping mechanism to stabilize updates; (3) \textit{Navigation}: bridging the abstract policy to real-world control. We demonstrate that \textit{SAGE} significantly improves navigation performance, achieving a 53.21\% LLM-Match Success Rate on A-EQA (+9.7\% over baseline) and generalizing widely to real-world deployments.

Theory · Reinforcement Learning and Planning

Yikai Lu, Yifei Wu, Xinyu Lu, Tongxin Li

In the big-world regime, agents cannot be universally capable and their ability is inevitably specialized across a world in pieces. Consequently, standard uniform guarantees fail to distinguish between the understanding of critical bottlenecks and irrelevant failures. We first formalize this limitation by proving that *general agents are not universal*, rendering standard worst-case analysis uninformative. To overcome this, we introduce **structural certification**, a transition-local framework that maps bounded goal-conditioned performance to entry-wise guarantees on the agent's internal world model. Our main contribution is constructive. We provide algorithms that filter specific transitions using deep compositional goals and prove that a general agent on these goals has a structural world model with a $\mathcal{O}(1/n)+\mathcal{O}(\delta)$ error bound. Conversely, this bound is tight in the small-$\delta$ regime, whose existence is explicitly guaranteed by our certification. These results enable the certifiable deployment of general agents by localizing the specific transitions where long-horizon planning is reliable.

Theory · Reinforcement Learning and Planning

Runze Zhao, Yue Yu, Ruhan Wang, Chunfeng Huang, Dongruo Zhou

Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability to adapt to varying levels of problem difficulty remains poorly understood. In this work, we investigate the instance-dependent behavior of CTRL and introduce a simple, model-based algorithm built on maximum likelihood estimation (MLE) with a general function approximator. Unlike existing approaches that estimate system dynamics directly, our method estimates the state marginal density to guide learning. We establish instance-dependent performance guarantees by deriving a regret bound that scales with the total reward variance and measurement resolution. Notably, the regret becomes independent of the specific measurement strategy when the observation frequency adapts appropriately to the problem’s complexity. To further improve performance, our algorithm incorporates a randomized measurement schedule that enhances sample efficiency without increasing measurement cost. These results highlight a new direction for designing CTRL algorithms that automatically adjust their learning behavior based on the underlying difficulty of the environment.

Theory · Reinforcement Learning and Planning

Stefan Huber, Hannes Unger, Georg Schäfer, Jakob Rehrl

We analytically solve the Mountain Car problem, a canonical benchmark in RL, and derive an optimal control solution, closing a gap after 36 years. This enables us to reveal two surprising insights: The optimal control is quite simple, yet modern RL agents display a large gap to optimality. Motivated by the analysis of the optimal control, we introduce Chebyshev policies as a universal (i.e. dense) class of RL policies from first principles. They can be trained as drop-in replacements of neural nets, reducing the regret by a factor of 4.18, while requiring 268 times fewer parameters, fostering sample efficiency, explainability and real-time capability. Chebyshev policies are evaluated on further RL environments, including a real-world non-linear motion control testbed. They consistently improve performance over neural nets with PPO, ARS and REINFORCE. Our results demonstrate how Chebyshev policies offer a compelling and lightweight alternative or addition to neural nets for low-dimensional control tasks.

Applications · Chemistry, Physics, and Earth Sciences

Liao Chang, Luotian Yuan, Yiping Ke, Ying Wei

Multi-step retrosynthesis planning is a fundamental challenge in organic chemistry, defined by its enormous search space. Existing methods typically formulate it as a Markov Decision Process (MDP) with a fixed choice of transition model (i.e., a single-step retrosynthesis model), and focus on improving *how to search* through better policies and value functions. However, *how the transition space itself is navigated* remains largely unexplored. This limitation is particularly urgent given our observation of pronounced *skill disparity* among single-step prediction models: different models exhibit substantially different performance across molecule states. Motivated by this observation, we introduce RetrOrchestrator, an LLM-powered agent that explicitly accounts for model skill disparity by reframing retrosynthesis planning as a Partially Observable Markov Decision Process (POMDP). By regarding each single-step prediction model as a tool, we further propose a scaffold-aware reinforcement learning algorithm to optimize navigation policy within the transition space. As a result, RetrOrchestrator jointly searches which molecule to expand and which single-step model to apply for the molecule at the current step. Empirically, RetrOrchestrator significantly outperforms static baselines on the Retro*-190 benchmark, achieving a state-of-the-art 94.21\% success rate as well as a Pareto front in both wallclock time and number of model queries.

Applications · Robotics

Jinbang Huang, Zhiyuan Li, Yuanzhao Hu, Zhanguang Zhang, Mark Coates, Xingyue Quan, Yingxue Zhang

Large Language Models (LLMs) have recently shown strong promise for robotic task planning, particularly through automatic planning domain generation. Planning domains are brittle under imperfect logical states and perception noise; prior approaches largely treat generated planning domains as plan utilities, overlooking their potential as scalable sources of reasoning supervision and structured reward signals. At the same time, reasoning LLMs depend on chain-of-thought (CoT) supervision that is expensive to collect for robotic tasks, and reinforcement learning (RL) faces challenges on reward engineering. We propose Self-CriTeach, an LLM self-teaching and self-critiquing framework in which an LLM autonomously generates symbolic planning domains that serve a dual role: (i) enabling large-scale generation of robotic planning problem–plan pairs, and (ii) providing structured reward functions. First, the self-written domains enable large-scale generation of symbolic task plans, which are automatically transformed into extended CoT trajectories for supervised fine-tuning. Second, the self-written domains are reused as structured reward functions, providing dense feedback for reinforcement learning without manual reward engineering. This unified training pipeline yields a planning-enhanced LLM with higher planning success rates, stronger cross-task generalization, reduced inference cost, and resistance to imperfect logical states.

Theory · Reinforcement Learning and Planning

Min Wang, Xin Li, Ye He, Mingzhong Wang, Yonggang Zhang

Meta-Reinforcement Learning (Meta-RL) faces significant challenges in non-parametric settings, where vastly different return scales across diverse tasks cause severe gradient interference. Existing categorical solutions attempt to normalize these scales but often fail due to rigid discretization and quantization errors. To address this, we propose Reflect-then-Correct (RTC), a framework that models meta-values using Sinkhorn divergence. By treating distributions as adaptive floating particles, RTC achieves a geometry-aware alignment of distinct meta-task structures. However, while Sinkhorn updates harmonize gradients, they introduce statistical bias via sampling estimation. RTC overcomes this by ''reflecting'' on the temporal accumulation of Bellman inconsistencies through a recursive error model and ''correcting'' the optimization via adaptive importance weights that prioritize transitions critical for accuracy. We provide theoretical guarantees for this reweighting strategy and demonstrate that RTC outperforms existing baselines on the challenging Meta-World ML-10 and ML-45 benchmarks.

Reinforcement Learning · Multi-agent

Mingde Yao, Zhiyuan You, King-Man Tam, Menglu Wang, Tianfan Xue

With the recent fast development of generative models, instruction-based image editing has shown great potential in generating high-quality images. However, the quality of editing highly depends on carefully designed instructions, placing the burden of task decomposition and sequencing entirely on the user. To achieve autonomous image editing, we present PhotoAgent, a system that advances image editing through explicit aesthetic planning. Specifically, PhotoAgent formulates autonomous image editing as a long-horizon decision-making problem. It reasons over user aesthetic intent, plans multi-step editing actions via tree search, and iteratively refines results through closed-loop execution with memory and visual feedback, without requiring step-by-step user prompts. To support reliable evaluation in real-world scenarios, we introduce UGC-Edit, an aesthetic evaluation benchmark consisting of 7,000 photos and a learned aesthetic reward model. We also construct a test set containing 1,017 photos to systematically assess autonomous photo editing performance. Extensive experiments demonstrate that PhotoAgent significantly outperforms existing methods in both instruction faithfulness and visual quality across a diverse range of editing scenarios.

Reinforcement Learning · Planning

Shiyu Li, Yifan Wang, Peiming Li, Zheng Wei, Yang Tang

Search agents powered by Large Language Models have demonstrated significant potential in tackling knowledge-intensive tasks. Reinforcement learning has emerged as a powerful paradigm for training these agents to perform complex, multi-step reasoning. However, prior RL-based methods often rely on sparse or rule-based rewards, which can lead agents to commit to suboptimal or erroneous reasoning paths without the ability to recover. To address these limitations, we propose **ReSeek**, a self-correcting framework enabling search agents to recover from erroneous search paths during an episode. By invoking a special **JUDGE** action, the agent can judge the information and re-plan its search strategy. To guide this process, we design a dense, instructive process reward function, which decomposes into a correctness reward for retrieving factual information and a utility reward for finding information genuinely useful for the query. Additionally, to mitigate the risk of data contamination in existing datasets, we introduce **FictionalHot**, a contamination-free benchmark requiring complex reasoning. Experiments show ReSeek significantly outperforms SOTA baselines in task success and path faithfulness.