Reinforcement learning

Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.

6,940 stories · RSS feed

arXiv Machine Learning

Aug 18

Toward Optimal Second-Order Path-Length Guarantee for Adversarial Multi-Armed Bandits

arXiv:2608. 15996v1 Announce Type: new Abstract: We study second-order path-length regret in adversarial $K$-armed bandits against oblivious loss sequences.

By Mengxiao Zhang

reinforcement-learning safety

arXiv AI

Aug 18

Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics

arXiv:2608. 16182v1 Announce Type: cross Abstract: Deep Q-learning (DQL) has achieved remarkable empirical success in reinforcement learning, yet its training process remains notoriously unstable.

By Bozhou Chen, Yongyi Wang, Hanyu Liu, Xionghui Yang, Wenxin Li

reinforcement-learning safety

arXiv AI

Aug 18

Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning

arXiv:2608. 14963v1 Announce Type: cross Abstract: Pareto Conditioned Networks learn multiple multi-objective reinforcement learning behaviours by conditioning a single policy on a desired return command.

By Joanikij Chulev, Hendrik Baier

agents reinforcement-learning safety

arXiv AI

Aug 18

An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing

arXiv:2605. 13221v2 Announce Type: replace Abstract: In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC).

By Hanwen Zhang, Dusit Niyato, Wei Zhang, Xin Lou, Malcolm Yoke Hean Low

llms rag agents reinforcement-learning

arXiv AI

Aug 18

Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation

arXiv:2608. 16482v1 Announce Type: new Abstract: The dosing of intravenous fluids and vasopressors in sepsis is a sequential decision made under uncertainty and guided largely by clinical judgment, which makes it a natural target for reinforcement learning from historical care.

By Marc P\'erez-Roig, David Fern\'andez-Narro, Carlos S\'aez

reinforcement-learning

arXiv AI

Aug 18

PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning

arXiv:2508. 09521v3 Announce Type: replace-cross Abstract: Emotional support conversations require more than fluent responses.

By Yunxiao Wang, Meng Liu, Sicheng Zhao, Lizi Liao, Liqiang Nie

llms reinforcement-learning fine-tuning multimodal safety

arXiv AI

Aug 18

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

arXiv:2604. 06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes.

By Qihan Ren, Peng Wang, Ruikun Cai, Shuai Shao, Dadi Guo, Yuejin Xie, Yafu Li, Quanshi Zhang, Xia Hu, Jing Shao, Dongrui Liu

llms reinforcement-learning fine-tuning safety data-engineering

arXiv Machine Learning

Aug 18

Lipschitz Bandits with Arbitrary Feedback Delays

arXiv:2608. 15036v1 Announce Type: new Abstract: The Lipschitz bandit problem extends the traditional multi-armed bandit framework to continuous action spaces by assuming that the reward functions satisfy a Lipschitz condition.

By Yuhao Liu, Yu Chen, Longbo Huang

reinforcement-learning safety

arXiv AI

Aug 18

Learning from Unreachable Rewards: Hint-Conditioned Reinforcement Learning for Generative Recommendation

arXiv:2608. 11980v2 Announce Type: replace-cross Abstract: Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively generating this token sequence.

By Kangning Zhang, Haotian Fang, Xukun Luo, Hao Yin, Yang Gao, Peng Yan, Weiwen Liu, Weinan Zhang, Yong Yu

reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Aug 18

Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation

arXiv:2608. 15949v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled their use as conversational recommender systems (CRS), demonstrating strong recommendation accuracy and natural dialogue.

By Cedar Site Bai, Duanshun Li, Zhenyu Liao, Sheikh Sarwar, Huiyuan Chen, Yuan Chen, Changhe Yuan, Haiyang Zhang, Qilin Qi

llms agents reinforcement-learning fine-tuning

arXiv Machine Learning

Aug 18

DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance

arXiv:2608. 14644v1 Announce Type: new Abstract: Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant.

By Zihan Li, Feifei Li, Wenhui Que

llms rag reinforcement-learning fine-tuning efficiency benchmarks safety

arXiv AI

Aug 18

TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents

arXiv:2608. 16156v1 Announce Type: new Abstract: Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult.

By Huan Zhang, Mingju Chen, Dongxu Zhou, Can Lv, Heng Chang, Sen Cui, Faguo Wu, Shiji Zhou

llms agents reinforcement-learning benchmarks

arXiv Machine Learning

Aug 18

TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH

arXiv:2608. 16410v1 Announce Type: new Abstract: Combined algorithm selection and hyperparameter optimization (CASH) searches a conditional space in which the selected model determines which hyperparameters are active.

By Yu-Han Huang, Yujia Wu, Vincent S. Tseng

reinforcement-learning

arXiv AI

Aug 18

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models

arXiv:2603. 24575v2 Announce Type: replace-cross Abstract: Scalable Vector Graphics (SVG) are essential for technical illustration and digital design, offering resolution independence and semantic editability.

By Qijia He, Xunmei Liu, Hammaad Memon, Ziang Li, Zixian Ma, Jaemin Cho, Zhongzheng Ren, Daniel S Weld, Ranjay Krishna

llms rag reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Aug 18

Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies

arXiv:2601. 02754v3 Announce Type: replace-cross Abstract: With the rapid development of e-commerce, auto-bidding has become a key asset in optimizing advertising performance under diverse advertiser environments.

By Mingming Zhang, Na Li, Zhuang Feiqing, Hongyang Zheng, Jiangbing Zhou, Wang Wuyin, Sheng-jie Sun, XiaoWei Chen, Junxiong Zhu, Lixin Zou, Chenliang Li

llms reinforcement-learning benchmarks

arXiv AI

Aug 18

SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation

arXiv:2605. 17648v2 Announce Type: replace Abstract: Generative recommendation treats next-item prediction as autoregressive item-identifier generation.

By Zaiyi Zheng, Liang Wu, Guanghui Min, Yaochen Zhu, Liangjie Hong, Chen Chen, Jundong Li

reinforcement-learning

arXiv AI

Aug 18

When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction

arXiv:2608. 15592v1 Announce Type: new Abstract: Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput.

By Feiyang Ren, Shengtao Wen, Lingbing Guo, Yu Tian, Yuanning Cui, Xiang Chen

llms reinforcement-learning efficiency benchmarks

arXiv AI

Aug 18

Leveraging Machine Unlearning for Cost-Efficient Preference Alignment

arXiv:2504. 06659v2 Announce Type: replace-cross Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like reinforcement learning with human feedback face notable challenges.

By Xiaohua Feng, Yuyuan Li, Huwei Ji, Jiaming Zhang, Li Zhang, Tianyu Du, Chaochao Chen

llms reinforcement-learning safety

arXiv AI

Aug 18

HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL

arXiv:2608. 16837v1 Announce Type: cross Abstract: Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation.

By Langzhe Gu, Chengkai Hou, Meng Li, Xinhua Wang, Jiaming Liu, Xinyuan Lv, Bowei Zhang, Shuanghao Bai, Guangrun Li, Jingyang He, Gaole Dai, Ziluo Ding, Zhiyuan Xu, Kuan Cheng, Jian Tang, Zhengping Che, Shanghang Zhang

rag agents reinforcement-learning robotics multimodal safety

arXiv AI

Aug 18

Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning

arXiv:2608. 16831v1 Announce Type: new Abstract: Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a fixed model could adapt its behavior from instructions and demonstrations.

By Minh-Ha Nguyen, Cathy Shyr

llms reinforcement-learning benchmarks

Get the daily briefing