Reinforcement_Learning
-
KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents
2026-10-15 17:52:33Siqi Chen, Zhengxi Lu, Yuchen Yan, Xingyu Wu, Qipeng Chen, Xin Zhang, Aiting Liu, Chao Deng, Jie Liu, Jin Ma, Weiming Lu, Jun Xiao, Yongliang ShenAbstract
Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions is fundamentally difficult. Outcome-based reinforcement learning provides only a single terminal reward shared across an entire trajectory. Recent process-supervision methods aim to assign credit at finer granularity, but they typically anchor credit to either surface-level trajectory states or model-internal signals, both of which become unreliable in deep search where observations are heterogeneous and retrieved contexts are long and noisy. We propose KnowGPO, a reinforcement learning framework that aligns trajectories by the task-relevant knowledge they have acquired rather than by their surface observations. For each query, KnowGPO decomposes the information required to derive the answer into atomic knowledge conditions, and represents the state of a trajectory at each step by the subset of conditions it has satisfied. Trajectories sharing the same knowledge state are grouped for within-group comparison, and the incremental knowledge gain between consecutive steps serves as an environment-grounded process reward. Experiments on Xbench, BrowseComp-ZH, and GAIA show KnowGPO consistently outperforms outcome-only (GRPO) and process-supervision baselines (GiGPO, IGPO) by 3.8 to 4.2 points, with our 8B model rivaling or exceeding most 32B open-source systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22331
PDF
-
Training Reasoning Models to Generate Diverse Scientific Ideas
2026-10-15 17:52:12Manya Wadhwa, Pranav Narayanan Venkit, Hiroaki Hayashi, Yu Li, Tuhin Chakrabarty, Chien-Sheng WuAbstract
One of the first steps of a research pipeline is generating ideas. Large Language Models (LLMs) are increasingly used to automate this step, but most of this work optimizes the quality of individual ideas, while overlooking diversity. In our work, we study document-grounded ideation, focusing on increasing the diversity of LLM generated ideas and ensuring they are high quality. Given prior papers, a model must propose a set of ideas that are each high-quality and clearly distinct from one another, while also being grounded in the input documents. To optimize for this, we propose training with a set-level reinforcement learning objective. In our setup, in a single generation, the model writes K structured idea cards grounded in the source papers, and the set is scored jointly, where each idea's quality is weighted by its distance from the ideas written before it. This teaches the model to steer each new idea away from its predecessors. We show that our trained 8B model achieves higher creative utility (a measure combining quality and diversity) than Claude Opus 4.8 and GPT-6 Astra on our contamination-free benchmark. In a pilot human study with four experts, our sets are judged as promising as Claude Opus 4.8's and contain marginally more unique ideas. When a coding agent runs proof-of-concept experiments on the ideas, our model's success@k is comparable to Claude Opus 4.8's, so we see that the added diversity does not cost any executability.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22324
PDF
-
Learning to Steer LLM Agents and Multi-Agent Systems
2026-10-15 17:51:17Leyang Shen, Yaxin Gong, Yang Zhang, Chenxiao Fan, Jiakai Wang, Dong Wang, Yang Liu, Fuli Feng, Chun Kai Ling, Tat-Seng ChuaAbstract
Large language model (LLM)-based agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collaboration. However, these systems are prone to deviating from the overall goal as execution unfolds, which wastes execution resources and leads to undesired outcomes, a failure termed goal drift. In this work, we propose a steering agent that supervises execution on the fly and steers the system back on track when drift occurs. The steering agent observes the execution context, deciding when to intervene with a low-cost fast path and how to intervene with a high-cost slow path. To unlock its steering intelligence, the ability to assess goal drift and generate effective interventions, we jointly train the two paths with reinforcement learning, combining a pairwise ranking objective with group-relative policy optimization (GRPO). Experiments on information-seeking search tasks show that the steering agent provides effective supervision for both single-agent and multi-agent systems, improving their performance and efficiency. The learned steering intelligence generalizes to out-of-domain tasks, transfers to unseen executors, and supports controllable intervention frequency without retraining.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22316
PDF
-
Towards Continual Learning: Mitigating Forgetting With Subspace Tuning
2026-10-15 17:44:43Arnav Chavan, Kusha Sareen, Rishabh Tiwari, Abhranil Chandra, Johan Obando-Ceron, Kurt Keutzer, Scott Niekum, Inderjit S Dhillon, Devvrit KhatriAbstract
Large language models (LLMs) acquire new skills through fine-tuning, but it can destroy capabilities they already have: catastrophic forgetting remains a central obstacle to continual learning in LLMs. Recent works connect forgetting to how far, and along which directions, fine-tuning moves the weights. On-policy methods such as reinforcement learning and on-policy distillation avoid updating the principal singular directions of weight matrices and thus forget less. In contrast, SFT concentrates updates along these directions and is susceptible to catastrophic forgetting. In this work, we introduce Subspace Tuning (SST), which restricts each weight update to the bottom singular subspace, eliminating changes along the principal directions. SST is optimizer-agnostic and composes well with fine-tuning recipes including SFT and self-distillation. SST combines tight subspace protection, dense gradient estimation, and a simple refresh mechanism, enabling stronger learning than prior orthogonal fine-tuning methods. With these mechanisms, protecting as much as 99\% of the weight subspace substantially improves retention while preserving strong target-task performance. This behavior strengthens with model and data size and nearly eliminates forgetting in the large-model regime. SST also keeps the model close to its base distribution, inducing $2$--$4\times$ less KL drift than the baseline recipes. Overall, SST advances the learning--forgetting Pareto frontier, making it a practical default for fine-tuning pre-trained language models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22293
PDF
-
EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search
2026-10-15 17:43:31Hanane Nour Moussa, Doeun Lee, Sachin KumarAbstract
Reinforcement learning has become a common post-training technique to improve the accuracy of LLMs on verifiable tasks. However, such training can narrow the set of solutions the model can produce. Several approaches have attempted to address this behavior-sharpening effect, but they often optimize metrics that do not reflect the diversity of correct solutions. Ideally, we want a model that can produce multiple good solutions, not only a single reliable one. We propose EliteReplay, a post-training recipe that pairs GRPO with an "elite" archive built by quality-diversity search. Before training, we use the frozen base model to collect solutions that span distinct approaches; during training, GRPO is combined with a replay loss on this archive. The result is a post-trained model that improves accuracy while preserving more of the base model's solution diversity. On multiple text-to-SQL tasks, EliteReplay achieves a higher pass@128 than all baselines, producing up to 77% more distinct correct strategies than the strongest baselines. It preserves most of the base model's correct strategies, outperforming existing methods in strategy retention. This diversity translates into practical benefits on ambiguous questions, where EliteReplay covers both interpretations nearly twice as often as the strongest baseline on AmbiQT.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22290
PDF
-
Routing Policy Optimization for Online Diffusion Reinforcement Learning
2026-10-15 17:40:30Qiuhong Shen, Yiding Yang, Yuxin Zhang, Xinwei Huang, Minxuan Lin, Bo Liu, Hao Kang, Haotian Yang, Yizhi Wang, Chongyang Ma, Xinchao WangAbstract
Reinforcement learning can align visual generators with reward signals beyond their pretraining objectives, but existing score-function methods typically introduce stochasticity by perturbing the reverse denoising trajectory, leading to costly rollout-based optimization. We instead ask whether stochastic exploration can be introduced inside the generator while preserving its original sampler. Routing Policy Optimization (RPO) answers this question by turning attention routing into a stochastic exploration action. At a few selected denoising levels, each query block keeps its own block and samples further key blocks in proportion to the generator's native attention mass, or keeps dense attention. The sampled route perturbs the velocity of that transition, and a Gaussian likelihood around the dense velocity scores the perturbation with a score-function objective. RPO further uses a controlled two-rollout estimator: two rollouts share the same prompt, initial latent, routed denoising levels, and dense anchor layers, differing only in their sampled attention routes. Their reward difference provides an advantage signal for the routed transitions. Because the likelihood differentiates the dense velocity itself, the learned updates remain effective after routing is removed. At inference, RPO restores dense attention and retains the original deterministic sampler. Experiments on text-to-image and text-to-video generation show that RPO improves generation quality while achieving nearly 4x higher training efficiency than Flow-GRPO-style methods. Please see our project page at this https URL for visual results.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22282
PDF
-
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
2026-10-15 17:35:17Anikait Singh, Teresa Zhang, Yoonho Lee, Roshen Sanjay Nair, Aviral Kumar, Chelsea FinnAbstract
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, cross-document reasoning at inference time, while precomputed structures like knowledge graphs often fall short because they rely on rigid heuristics. Instead, can we allow agents to perform anticipatory directed curation: learning to proactively reorganize unstructured corpora prior to inference to efficiently serve diverse future queries. We build on a key asymmetry in modern agentic harnesses (e.g., Claude Code): while LLM agents are adept at navigating existing filesystems to solve an immediate task, they are rarely trained to construct reusable workspaces for future use. To instantiate this capability, we introduce Librarian Agents, a framework in which a builder agent transforms raw documents into a hierarchical filesystem of synthetic files and reference links, which forms a workspace tailored for a downstream answering agent. We formulate workspace construction as a Markov decision process and optimize the builder policy via reinforcement learning to directly maximize downstream answering accuracy. Empirically, Librarian Agents outperforms the strongest retrieval and precomputation baselines by 33 percentage points on BrowseComp-Plus, amortizes upfront construction costs across repeated queries, and generalizes zero-shot to unseen domains on BRIGHT with a 31-point average accuracy improvement.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22273
PDF
-
X-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning
2026-10-15 17:34:17Adhwaa Al-Chaab, Ayman Younis, Dario PompiliAbstract
The O-RAN ALLIANCE introduces architectural flexibility through disaggregation and AI-driven control. While the RAN Intelligent Controller (RIC) enables centralized optimization, current AI approaches lack reasoning capabilities and explainability. We propose eXplainable RIC (X-RIC), a novel framework integrating agentic AI into O-RAN architectures. X-RIC combines reactive Reinforcement Learning (RL) with strategic agentic reasoning through: (i) automated Behavioral Cloning (BC) using domain heuristics for sample-efficient training, (ii) a Telecom Language Model (TLM), a transformer-based reasoning module providing contextual abstraction and interpretability, and (iii) closed-loop co-adaptation within the Near-RT RIC control loop enabling continuous policy refinement. To ensure deployment readiness, we introduce BARX (Benchmarking Agentic Reasoning for RAN), a domain-specific evaluation framework assessing agentic control across latency, compliance, and determinism metrics. We validate X-RIC on SLA-aware network slicing in simulation and O-RAN-compliant testbed deployments. X-RIC achieves 89% operational cost reduction while maintaining SLA compliance, converging 75% faster with 50% fewer training steps and 46% lower variance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22269
PDF
-
SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation
2026-10-15 17:30:28Yufei Jiao, Jinfa Huang, Zeyue Xue, Tianyu Xie, Yuexiao Ma, Rongrong Ji, Xiawu Zheng, Jiebo LuoAbstract
Reinforcement learning (RL) enables language models to improve text-to-image (T2I) generation by rewriting prompts for a frozen image generator. Existing methods typically apply a single signal derived from the image to individual subword tokens, although objects, counts, attributes, and relations form coherent semantic spans. We propose SCOPE, an objective based on Group Relative Policy Optimization (GRPO) that aligns update weighting with this structure. The rewriter jointly generates an enhanced prompt and its semantic partition. SCOPE pools shifts in policy log probabilities within each span to derive a shared coefficient for its token losses while retaining a single advantage for each completion. It requires neither separate span rewards nor additional image renders. Across Qwen-Image, SD3, and FLUX.1-dev, SCOPE achieves average relative gains over vanilla GRPO of 9.48% on GeneVal and 7.62% on T2I-CompBench. Ablation studies show that both semantic boundaries and pooling within spans contribute to these gains, supporting semantic structure as a practical inductive bias for prompt engineering with RL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22264
PDF
-
MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents
2026-10-15 17:16:18Huanyao Zhang, Jiepeng Zhou, Jiaye Lin, Ontai Tang, Jingtian Hao, Mugeng Liu, Ru Peng, Lang Mei, Xiaohan Yu, Liyan Liu, Chong Chen, Wentao ZhangAbstract
Multimodal deep search is moving from short queries to long-horizon investigations that continually acquire evidence. However, training such agents remains constrained by limited challenging training questions and insufficient process feedback. We introduce MMSearch-OPD, combining controllable data refinement with joint reinforcement learning (RL) and on-policy distillation (OPD). Our Refine pipeline performs targeted expansion of reasoning chains derived from existing simple multimodal questions. Parameterized transformations control search depth and cross-modal evidence requirements while reusing existing image--question pairs. For training, answer rewards and lightweight behavior penalties guide RL, while the reward gap modulates token-level teacher guidance on imperfect student trajectories. An exponentially decaying distillation coefficient reduces teacher dependence as training proceeds. Experiments show gains from data refinement and further improvements from joint training after SFT, indicating stronger long-horizon multimodal deep search capabilities.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22240
PDF
-
Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models
2026-10-15 17:01:41Yuqi Xiong, Chunyi Peng, Zhipeng Xu, Qing Yang, Zhenghao Liu, Zulong Chen, Yu Gu, Ge YuAbstract
Reinforcement learning (RL) can elicit specialized visual capabilities in vision-language models (VLMs), yet jointly optimizing heterogeneous objectives often introduces cross-capability gradient conflicts. Training experts independently mitigates this interference, but direct reward optimization may entangle specialized knowledge with reward-hacking biases. This paper proposes Skill-Decoupled On-Policy Expert Distillation (SCOPED), which trains capability-specific experts and extracts explicit skills through reward-guided reflection. During on-policy distillation, these skills guide expert supervision while remaining unavailable to the unified student, encouraging it to internalize procedural knowledge without explicit skills at inference time. Across eight multimodal benchmarks, SCOPED consistently outperforms the backbone and mixed-capability RL, demonstrating the effectiveness of skill-decoupled on-policy expert distillation for integrating independently acquired capabilities. Further analyses reveal interference during joint capability optimization and suggest that skill augmentation promotes more consistent expert trajectories, greater attention to task-relevant visual evidence, and better preservation of specialized expertise in the unified student. All code and data are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22217
PDF
-
Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory Writing
2026-10-15 16:46:47Tianxiang Fei, Jiazheng Kang, Mao Zheng, Xingyan He, Xiang YuAbstract
External-memory systems extend language-model applications beyond a context window, but their quality depends critically on the model executing the write path: deciding what to retain, how precisely to represent it, and how new evidence should update persistent state. Existing frameworks typically place a general-purpose large language model behind framework-specific prompts. This raises serving cost, and a writer specialized for one protocol does not transfer directly to another; a unified model that can operate across established memory frameworks remains largely unexplored. We present Hy-Memory-30B-A3B, a compact long-term-memory writer trained across Mem0, MemOS, and Hy-Memory. Memory On-Policy Distillation teaches framework-specific write protocols on student-generated states; Memory RL then optimizes downstream answerability using dense per-chunk probes, attributed cross-chunk rewards, over-storage controls, and chunk-level GRPO. Carrying policy-written banks across windows keeps training aligned with deployment. On fixed 20% benchmark subsamples, Hy-Memory-30B-A3B ranks first on all four evaluated harnesses, including held-out EverMemOS, with a 55.49% macro average versus 54.62% for Claude Opus 5.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22196
PDF
-
Mosaic: Multi-Session Agentic Reinforcement Learning
2026-10-15 16:32:44Yilong Xu, Minrui Xu, Xinyu Zhou, Xiang Long, Haochen Tan, Zhijiang GuoAbstract
Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context. However, agentic techniques such as context compaction and subagent forking may produce trajectories spanning multiple sessions, creating a mismatch between the single-session training assumption and inference-time execution. Therefore, we introduce Multi-Session Agentic Reinforcement Learning, a more general setting that supports an arbitrary number of sessions within a trajectory. Under this setting, a widely adopted method is to broadcast trajectory-level advantages to all sessions, but this does not distinguish contributions from various sessions or guide session allocation within trajectories. To address this issue, we propose Mosaic, a multi-session agentic RL method with critic-free hierarchical optimization. At the trajectory level, it incorporates session-usage signals into advantage estimation. At the session level, it shapes each session's advantage according to the estimated marginal contribution. Experiments on BrowseComp with Qwen3.5-4B show that Mosaic outperforms broadcasting in both context compaction and subagent forking scenarios while using fewer sessions on average. Further analyses show that our method achieves improvements in session utility and allocation, which we suggested is a promising target for future advances in multi-session agentic RL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22174
PDF
-
Specification Gaming and a Constrained Reinforcement Learning Mitigation in a Cleaning Gridworld
Abstract
Reinforcement learning agents optimize exactly the reward signal they are given, which can diverge sharply from an intended true objective when that signal is only a proxy for it; this failure mode is known as specification gaming. Existing evidence for this failure mode is largely observational, with comparatively few demonstrations pairing a controlled, deliberately constructed proxy/true gap with a mitigation that carries a verifiable guarantee rather than only an empirical improvement. We construct a minimal gridworld in which a cleaning-robot agent can either genuinely remove dirt or conceal it from a cheap sensor, and show that a standard deep Q-network trained only on the sensor's proxy reward converges to a policy that games it completely, reaching near-maximal proxy reward while never achieving the true objective. We then introduce a constrained reinforcement learning fix, penalizing the specific behaviors through which the agent exploits the gap, and show that it eliminates the gaming behavior from the final policy while substantially recovering true-objective performance. We further derive and empirically verify an exact accounting identity relating the proxy reward, true reward, and our cost signal for this environment, showing that the cost signal measures the proxy/true gap exactly rather than merely tracking it, and yields a deterministic guarantee under a hard-constrained variant of the method.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22152
PDF
-
TIPS: A Tiny Inference-time Policy for Scaling in Diffusion Language Models
2026-10-15 15:46:55Ya-Shi Zhang, Jian Tang, Pierre-Andr\'e No\"el, Oleksiy OstapenkoAbstract
Masked diffusion language models expose an inference-time choice: which positions become visible after each denoising pass. Many existing decoding methods use hand-designed rules or require visibility to grow monotonically. We present a $\textbf{T}$iny $\textbf{I}$nference-time $\textbf{P}$olicy for $\textbf{S}$caling ($\textbf{TIPS}$), an approximately $600$K-parameter controller that learns both unmasking and remasking while keeping the underlying language model frozen. TIPS uses visibility-aware confidence features and a shallow transformer to select which tokens should be visible, while a fixed schedule controls the expected visible fraction. We train the controller through supervised warmup followed by reinforcement learning from terminal correctness rewards. On GSM8K and MATH-500 with LLaDA-8B-Instruct, the full-canvas and two-block TIPS variants achieve $58.46\%$ and $57.97\%$ micro-averaged accuracy at a budget of $32$ decoder evaluations, exceeding the strongest baseline in our main comparison by $12.1$ and $11.6$ percentage points, respectively. Both variants are trained at a budget of $32$ evaluations and remain competitive at higher budgets without retraining. These results demonstrate that learning when to reveal and reconsider tokens can improve the accuracy-compute trade-off without updating the decoder backbone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22099
PDF
-
Progress Reward Model for Reinforcement Learning via Large Language Models
2026-10-15 15:21:25Xiuhui Zhang, Ning Gao, Xingyu Jiang, Yihui Chen, Yuheng Pan, Mohan Zhang, Yue DengAbstract
Traditional reinforcement learning (RL) algorithms face significant limitations in handling long-term tasks with sparse rewards. Recent advancements have leveraged large language models (LLMs) to enhance RL by utilizing their world knowledge for task planning and reward generation. However, planning-based approaches often depend on pre-defined skill libraries and fail to optimize low-level control policies, while reward-based methods require extensive human feedback or exhaustive searching due to the complexity of tasks. In this paper, we propose the Progress Reward Model for RL (PRM4RL), a novel framework that integrates task planning and dense reward to enhance RL. For high-level planning, a complex task is decomposed into a series of simple manageable subtasks, with a subtask-oriented, fine-grained progress function designed to monitor task execution progress. For low-level reward generation, inspired by potential-based reward shaping, we use the progress function to construct a Progress Reward Model (PRM), providing theoretically grounded optimality and convergence guarantees, thereby enabling effective policy optimization. Experimental results on robotics control tasks demonstrate that our approach outperforms both LLM-based planning and reward methods, achieving state-of-the-art performance. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22056
PDF
-
WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents
2026-10-15 15:12:56Weihao Li, Zihang Xu, Zhongqiu Wang, Songwei Yu, Wenqiang Zhu, Yuechen Luo, Jingxuan Xu, Yanan Wu, Haoyang Huang, Ken DengAbstract
Real-world software engineering rarely consists of isolated changes. Features, migrations, and systematic fixes often unfold across multiple pull requests (PRs), requiring coordinated modifications across a repository. Yet most executable repository-level benchmarks retain a single issue or PR as the task unit, while existing multi-PR settings rely on coarse aggregation and structure-agnostic evaluation. This mismatch obscures dependencies among changes and limits progress measurement and learning signals for long-horizon code agents. We introduce WEAVE, a framework that transforms verified PR histories into executable, dependency-structured tasks. WEAVE leverages repository-calibrated typed change loci to organize related PRs into bounded DAGs and instantiate each as a unified executable task. We further introduce Graph Credit, a deterministic, test-grounded metric that measures dependency-consistent partial progress and supports dense, verifiable rewards for reinforcement learning. Experiments on task construction, agent evaluation, supervised fine-tuning, and reinforcement learning show that WEAVE yields coherent executable tasks, enables more faithful progress measurement than flat scoring, and provides effective supervision and verifiable rewards for training code agents.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22039
PDF
-
Learning Rewards in Strategic Games
2026-10-15 13:59:45Antoine Bergerault, Cyrille Kone, Giorgia RamponiAbstract
Understanding the objectives that drive agents' behavior is crucial in strategic environments, where multiple agents interact and adapt to one another. This challenge arises in domains such as cybersecurity, autonomous driving, and online markets, where agents' underlying incentives are typically unknown and must be inferred from their observed behavior. Inverse reinforcement learning (IRL) provides a natural framework for this problem, but extending IRL to strategic multi-agent settings introduces a fundamental challenge: a reward that explains observed behavior does not necessarily induce optimal strategies when used for decision-making. In this work, we study this problem through the lens of \emph{strategic identifiability}, and show that learning from a fixed policy pair can be insufficient to strategically identify rewards, independent of the number of expert samples $K$. Motivated by this, we introduce an active IRL algorithm for two-player repeated Stackelberg games, in which the leader adaptively selects policies to elicit informative responses about the follower's reward. Combining maximum-likelihood estimation with experimental design, we derive finite-sample guarantees on the Stackelberg sub-optimality induced by the learned reward, matching up to polylogarithmic factors a new minimax learning rate of $K^{-1/2}$. Finally, we evaluate our approach in a realistic anti-poaching setting, demonstrating the benefits of active exploration for reward recovery and downstream strategic performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21912
PDF
-
Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents
2026-10-15 13:41:18Hanzhen Wang, Boxiang Lyu, Zhongxiang Dai, Siyang Gao, Dake Zhang, Shuang QiuAbstract
Risk-sensitive reinforcement learning (RL) addresses decision-making under uncertainty and adverse outcomes. Learning risk-sensitive policies from fixed datasets is important when additional interaction with the environment is costly. Existing work on risk-sensitive RL focuses on online settings or specific risk measures, leaving a general theoretical understanding of its offline setting underdeveloped. In this work, we investigate efficient offline risk-sensitive RL using the optimized certainty equivalent (OCE), a general class of risk measures. We consider two formulations: dynamic-OCE RL, which applies OCE recursively at each step, and static-OCE RL, which applies a single OCE to the cumulative rewards. Under the tabular setting, we develop pessimistic value-iteration algorithms for both formulations and establish tight sublinear suboptimality bounds, explicitly capturing how risk sensitivity, encoded by utility functions, affects learning difficulty. Moreover, we establish minimax suboptimality lower bounds to characterize the problem's fundamental limits. To handle large state spaces, we further develop pessimistic least-squares value-iteration algorithms that incorporate the general OCE risk criterion into linear function approximation. We establish utility-dependent sublinear guarantees with explicit dependence on the feature dimension $d$. To our knowledge, we provide the first offline algorithms along with the first upper and lower suboptimality bounds for both dynamic- and static-OCE RL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21870
PDF
-
Learning to Think and Explore in 3D World
2026-10-15 12:38:48Yijiang Li, Bingyang Wang, Nuno VasconcelosAbstract
We study how vision-language models (VLMs) can learn to think and actively explore in 3D space. Instead of providing multi-view images, videos, or 3D representations to the model, we preserve the native visual encoding of VLMs, i.e., a single image, one at a time, just like humans, and treat the 3D representation only as an environment with which the model can interact through actions (e.g., move left) and observations (rendered images). Each rollout begins from an initial first-person view and a visual question. The model can then iteratively reason, navigate, and reorient its viewpoint before committing to a final answer. Following an initial trajectory-supervised finetuning, we apply reinforcement learning (RL) with rewards driven primarily by final-answer correctness. Crucially, RL provides no direct supervision over which viewpoints the model should visit or which exploration actions it should take. Instead, the model must learn an effective exploration policy solely from the extent to which its interactions improve performance. Across six 3D benchmarks, our model ACT3D achieves an average accuracy of 53.2% that improves its base Qwen model by 22.0% and surpasses proprietary Gemini 3.6 Flash. ACT3D also outperforms existing open-source 3D methods while using 50-70% fewer input frames, and generalizes to unseen domains with an average improvement of 5.9% over its supervised initialization. Further analysis reveals adaptive, question-conditioned exploration. Performance gains over the base model increase from 0.6% on questions answerable from the initial view to 16.3% on those requiring extensive exploration. ACT3D searches for occluded targets, avoids unnecessary exploration, and acquires complementary viewpoints for spatial comparisons. These findings demonstrate that outcome-based RL enables VLMs not only to reason over visual evidence, but also to learn when and how to acquire it.
Abstract (translated)
URL
https://arxiv.org/abs/2610.21783
PDF
