The paper introduces an exploration-guided prompt scaffolding framework for multimodal large language models, dynamically adjusting the prompt distribution during reinforcement learning post-training. It uses an Exploration Potential Score (EPS) derived from KL-regularized policy improvement to assess prompt utility without extra overhead, and a teacher model rewrites low-utility prompts to preserve intent while improving informativeness. Experiments on Geo3K, MMK12, MathVision, and MMMU-Pro show consistent performance gains, up to 9.7% in-domain and over 11% on out-of-distribution benchmarks.
By Yuanhao Yue, Qianli Ma, Chengyu Wang, Haoting Wang, Lei Shen, Jun Huang
The paper introduces new evaluation metrics for safe reinforcement learning that go beyond average safety guarantees by examining how often and how severely safety bounds are violated, consistency across tasks and bounds, and the relationship between training-time and final policy behavior. It also proposes a safety tier system for categorizing algorithms and presents empirical safety evaluations on multiple navigation tasks. The authors recommend reporting aggregate metrics, distributional data, and task‑specific results together, and provide an open‑source suite, SafeRLEval, to facilitate reliable safety assessment.
By Lindsay Spoor, Aske Plaat, Thomas Moerland
arXiv:2609.14261v1 Announce Type: cross
Abstract: Recent robot learning paradigms increasingly rely on large offline datasets of robotic interactions to train control policies. Expressive generative...
By Prajwal Koirala, Mark Campbell
arXiv:2609.14567v1 Announce Type: cross
Abstract: Reinforcement learning (RL) has shown considerable promise for robotic decision-making, yet deploying multi-agent RL (MARL) on physical multi-robot s...
By Abdalwhab Bakheet Mohamed Abdalwhab, Giovanni Beltrame, David St-Onge
HISPO introduces a segment‑level policy‑optimization technique for reinforcement learning with verifiable rewards, creating entropy‑derived contiguous segments during rollout and applying clipped importance‑sampling correction at this granularity. It bridges the gap between token‑level and sequence‑level corrections, offering a middle‑ground approach for credit assignment in long‑form mathematical reasoning. Evaluated on Qwen3‑1.7B‑Base across six benchmarks, HISPO consistently outperforms or matches the strongest baselines in Pass@8 and Acc@8 metrics, notably improving AIME25 scores over GRPO and GSPO.
By Quoc-Vinh Lai-Dang, Hyo-Sang Shin
arXiv:2609.13901v1 Announce Type: cross
Abstract: Multi-charger scheduling in wireless rechargeable sensor networks must weigh sensor death risk, charger energy, travel cost, return-to-base feasibili...
By Liang-Ching Tao, Pi-Chung Wang
The paper introduces SaLT-DPO, a Segment‑aware Listwise Target DPO method designed to improve safety in Large Reasoning Models (LRMs). It decomposes responses into reasoning and answer segments, scores each segment’s safety, and aligns length‑normalized rewards with soft target distributions over multiple candidates. The approach also incorporates joint safety coherence regularization and utility anchoring to reduce unsafe content while maintaining compliance and reasoning performance.
By JungMin Yun, Junehyoung Kwon, Hayeong Ryu, Byeonggeuk Lim, Hoejoon Kwon, YoungBin Kim
The paper introduces Verifier-Gated Multi-Expert On-Policy Distillation (VG‑OPD), a method that assigns teacher supervision at the token level based on each expert’s counterfactual gain on a specific answer criterion. VG‑OPD localizes supervision where experts disagree most with the student and weights it by criterion importance, integrating this into a gated KL advantage for reinforcement learning. Applied to scientific reasoning, VG‑OPD achieves top performance on seven benchmarks for 4B and 8B models, outperforming prior multi‑teacher distillation approaches.
By Xun Xu, Zaixi Zhang
arXiv:2609.15064v1 Announce Type: new
Abstract: Reinforcement learning (RL) is widely utilized in large language model training to improve targeted capabilities, yet how RL reshapes a model remains p...
By Lingheng Du, Yiming Tang, Xufeng Duan, Dianbo Liu
CHAI for LLMs is a framework that improves large language models’ performance on code‑mixed translation tasks by using LLMs as annotators to create preference data, applying reinforcement learning from AI feedback, incorporating LLM‑generated domain knowledge for iterative refinement, and evaluating on real‑world datasets. The approach yields a 68.45% average win rate over state‑of‑the‑art open‑source models in human‑adjudicated tests. It demonstrates a scalable method to enhance code‑mixed language understanding in open‑source LLMs.
By Wenbo Zhang, Aditya Majumdar, Asif Ekbal, Amulya Yadav
The paper introduces SCoRE, an agentic framework for Visual Retrieval-Augmented Generation that explicitly selects and consolidates visual evidence before generating answers. It addresses two key challenges: sparse, scattered evidence and noisy exploration trajectories that obscure reasoning. By maintaining a textual ledger of relevant observations and reloading original images for a logical evidence sequence, SCoRE decouples reasoning from exploration and enforces strict visual grounding, with training that rewards evidence coverage, compactness, and answer correctness.
By Yucheng Shen, Lingyong Yan, Jiulong Wu, Shuaiqiang Wang, Jianmin WU, Dawei Yin, Min Cao
arXiv:2609.15987v1 Announce Type: new
Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models (LLMs). We introduce Bellman Policy...
By Zhuoqing Song, Haotian Xu, Xikun Zhang, Lidong Bing
The paper introduces CREW, a collaborative multi‑agent reinforcement learning framework that automates the generation of the Related Work Section in research papers. Unlike previous methods that follow a fixed workflow, CREW allows large language model agents to dynamically select actions—Retrieve, Disseminate, Compose, and Critique—guided by a policy trained with Independent Proximal Policy Optimization. Experiments on a standard benchmark show that CREW improves output quality and reduces token usage compared to strong baselines.
By Hai-Dang Dang, Bao-Yen Pham, Bao Nguyen, Tran Thi Huong, Huynh Thi Thanh Binh
arXiv:2609.14557v1 Announce Type: new
Abstract: When performing parallel data transmission through a network using multiple paths, it is practically important to minimize the maximum transmission tim...
By Shunsuke Aoki, Atsuyoshi Nakamura
arXiv:2609.14968v1 Announce Type: new
Abstract: Online scheduling of dependency-aware tasks in heterogeneous cloud clusters is a fundamental yet challenging problem due to the complex interplay betwe...
By Tiangang Li, Shi Ying, Xiangbo Tian
arXiv:2609.13243v1 Announce Type: cross
Abstract: We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reprod...
By Amal Dev Haridevan, Junjie Kang, Jinjun Shan
The paper investigates whether large language model (LLM) agents can autonomously manage long‑horizon physical tasks without human intervention. It proposes a multi‑agent framework that combines planning, tool calling, observation, and verification, and tests it on agricultural tasks under varying weather conditions. Results show that zero‑shot LLM agents match reinforcement learning (RL) agents in the same environment and outperform RL when the environment shifts, suggesting a viable path for self‑adaptive physical AI.
By Varun Kaushik, Yayun Tan, Xiaofan Yu
arXiv:2609.13866v1 Announce Type: new
Abstract: Group-relative policy optimization (GRPO and descendants) can discard no-contrast rollout groups through dynamic sampling, while practical implementati...
By Juntao Yu
arXiv:2609.14327v1 Announce Type: new
Abstract: Variance penalization is a principled approach to risk-sensitive reinforcement learning (RL) that explicitly trades expected return for policy stabilit...
By Saunak Kumar Panda, Tong Li, Yisha Xiang, Ruiqi Liu
UniCAR‑RL is an annotation‑free reinforcement learning framework designed to improve multimodal large language models’ visual mathematics reasoning. It decouples perception and reasoning by using three branches: Caption‑RL for perception optimization, Reasoning‑RL for logical reasoning with a gold image description, and QA‑RL for end‑to‑end question answering. Experiments show significant gains in mathematical and visual reasoning across various model architectures and scales using only raw short‑answer data.
By Yuzhe Li, Hao Yan, Hao Wang, Xingchen Liu, Ya-Qi Yu, Jihao Wu, Minghui Liao, Wei Chen, Yuliang Liu