The paper proposes CANOPY, a minimalist reinforcement learning protocol that addresses two common pitfalls—signal starvation and policy drift—in outcome‑only RL for long‑horizon interactive tasks. By scaling same‑task exploration, keeping updates on‑policy, and anchoring updates with KL divergence, CANOPY enables a Qwen3‑14B agent to achieve top leaderboard results on the AppWorld coding benchmark without auxiliary supervision or elaborate scaffolding. The approach also improves performance on SWE‑bench for a Qwen3.5‑9B model.
By Liming Pu, Xiaoxia Li, Yifu Liu, Teng Cao, Bin Yang
arXiv:2608. 14642v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents trained on a single reward signal exploit the gap between the designed reward and the intended behavior.
By Prabhjyot Singh, Majid Ghasemi, Mark Crowley
arXiv:2606. 17043v1 Announce Type: cross Abstract: When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-transition supervision.
By Tongyan Fang, Siyuan Huang, Naiyu Fang, Ganlong Zhao, Zhongjin Luo, Jianbo Liu, Xiaogang Wang, Ying Dong, Hongsheng Li
arXiv:2609. 12014v1 Announce Type: new Abstract: Safe offline reinforcement learning assumes a cost function on every transition.
By Adam Haroon, Cody Fleming
arXiv:2608. 06735v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution.
By Senhao Wang, Chenghao Cai, Haitao Hu, Mingxing Huang, Xingguang Wang, Wenhao Li, Zecheng Lin
The paper introduces SAGE, a framework that selectively queries a Vision‑Language Model (VLM) teacher only when the learner is uncertain, using the teacher’s suggestions to guide training and distill them into a lightweight reinforcement learning policy. SAGE weights teacher actions by environment‑derived advantages, allowing the policy to improve beyond the imperfect VLM. Experiments on sparse‑reward visual reasoning and navigation tasks show that the learned policies can act without VLM guidance at evaluation, reduce VLM usage during training, and sometimes outperform the teacher itself.
By Matteo Merler, Giovanni Bonetta, Davide Zago, Rossella Cancelliere, Bernardo Magnini
arXiv:2607. 03702v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong decision-making capabilities in long-horizon interactive tasks, yet they still struggle to effectively leverage failed trajectories: full retries incur high interaction costs, while experience retrieval tends to dilute critical experience signals.
By Weiyang Guo, Zesheng Shi, Longhui Zhang, Zeen Zhu, Min Zhang, Jing Li
arXiv:2609.38889v1 Announce Type: new
Abstract: Constrained multi-agent control requires more than predicting rewarding actions: an action can cease to be executable as contact windows, shared capaci...
By Bo Yin, Dongbo Li, Hongkai Chen, Jie Liu, Guoliang Xing
arXiv:2607.08837v4 Announce Type: replace-cross
Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject...
By Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong
The paper introduces Reinforcement Learning with Verifiable Rewards (RLVR) applied to small search agents, specifically training a Qwen3.5-0.8B model with Group Relative Policy Optimization and an interleaved Wikipedia-search tool on the MuSiQue dataset. Experiments varying reward shapes across three seeds show that RLVR can achieve a 3.8‑fold improvement over an untrained baseline, with the best run reaching a 0.352 average exact match. The study finds that the sparse exact‑match reward, standard in larger models, performs poorly for small models, indicating that reward design must be tailored rather than scaled down from large‑model recipes.
By Gaurisankar Jayadas, Aske Plaat, \'Alvaro Serra-G\'omez, Sandheep P
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
By Wonjoong Kim, Yeonjun In, Sangwu Park, Dongha Lee, Chanyoung Park
The paper introduces Actor‑Critic with Action Chunking (AC2), a method that assigns credit to short action chunks instead of entire trajectories, enabling policy updates without waiting for terminal rewards. AC2 employs local readiness, reference solutions, and 10k‑token chunks to make critic‑based credit assignment reliable. Experiments on Qwen3‑4B with FineProofs‑RL show AC2 surpasses GRPO’s peak validation score while using 2.5× fewer decoding FLOPs and fewer training steps.
By Kaiyue Wen, Luke Bailey, Arvind Mahankali, Tengyu Ma