Reinforcement learning

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

3,427 stories · RSS feed

arXiv AI

1d ago

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

arXiv AI

1d ago

Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation

arXiv:2608. 15680v1 Announce Type: cross Abstract: Vision-language-action (VLA) models improve robotic manipulation but remain vulnerable to compounding errors, scene changes, and off-trajectory states.

By Yijie Xu, Haopeng Jin, Run Zhou, Shengbang Liu, Sixiang Chen, Hongyang Cheng, Sicheng Hu, Peterson Co, Jinwen Luo, Huajie Tan, Shanghang Zhang

reinforcement-learning robotics multimodal benchmarks

arXiv AI

1d ago

RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning

arXiv:2608. 15817v1 Announce Type: new Abstract: The growing ecosystem of large language models (LLMs) offers huge potential to optimize performance-cost trade-offs.

By Shihong Huang, Shengjie Wang, Hong Ma, Zhou Xu

llms reinforcement-learning benchmarks

arXiv AI

1d ago

A Shop Floor Production Scheduling Case based on RFID-supported Smart Factory

arXiv:2608. 16626v1 Announce Type: new Abstract: Radio frequency identification (RFID) technology has been widely implemented for real-time data collection in manufacturing shop floors, which, in turn, can be used to support dynamic shop floor production planning and scheduling.

By Zhihui Chen, Yize Sun, Yuhao Dong, Zeyu Xiao, Ray Y. Zhong

reinforcement-learning

arXiv AI

1d ago

Inference-Time Mitigation of Adversarial Political Bias in Large Language Models

arXiv:2608. 14629v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to political bias is a critical step towards safer and more trustworthy Artificial Intelligence (AI).

By Tejaswi V. Panchagnula, Bruce Coburn, Bryce J. Dietrich, Robert X. Browning, Edward J. Delp, Fengqing Zhu

llms nlp reinforcement-learning fine-tuning safety

arXiv AI

1d ago

LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset

arXiv:2608. 15175v1 Announce Type: cross Abstract: Uncrewed aerial vehicles (UAVs) are increasingly deployed for autonomous navigation in complex outdoor environments, where dynamic conditions and mission requirements require intelligent adaptive decision-making.

By Yousef Emami, Mohammadhossein Homaei, Hao Zhou, Miguel Guti\'errez Gait\'an, Atefeh Hajijamali Arani, Rui Zhang

llms agents reinforcement-learning

arXiv AI

1d ago

VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?

arXiv:2608. 15265v1 Announce Type: new Abstract: Constructing an interactive 3D open world from a user query is important.

By Yansong Ning, Jingwen Ye, Zhongkai Wu, Yang Sun, Yiqin Zhu, Xingyi Li, Weidong Zhang, Hao Liu

llms agents reinforcement-learning multimodal benchmarks

arXiv AI

1d ago

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

1d ago

Drive, Pack, Fly: The Travelling Thief Problem with Drone

arXiv:2608. 16435v1 Announce Type: new Abstract: In collection operations, accumulating payload progressively slows the vehicle, imposing a cumulative penalty on routing efficiency.

By Kabir Murjani, Abhay Sobhanan

reinforcement-learning robotics benchmarks

arXiv AI

1d ago

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

1d ago

CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs

arXiv:2608. 14791v1 Announce Type: new Abstract: Abductive reasoning, often characterized as inference to the best explanation, is central to explanation under uncertainty, from everyday sense-making and investigation to scientific discovery.

By Moein Salimi, Danial Parnian, Shaygan Adim, Amirmohammad Ebrahiminasab, Nima Alighardashi, Parsa Gholami, Sahand Akramipour, Mahdi Jafari Siavoshani, Mohammad Hossein Rohban

llms reinforcement-learning benchmarks

arXiv AI

1d ago

MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment

arXiv:2608. 14828v1 Announce Type: new Abstract: Aligning a language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additively, optimization collapses onto whichever is cheapest to improve and sacrifices the rest, so a support agent learns to sound warm while giving no real help.

By Tony Tu, Sayan Chakraborty, Ruomeng Xu, Tony Qin, Austin Tian

agents reinforcement-learning efficiency safety

arXiv AI

1d ago

Take it Personally: The Limits of General SSL Representations for Real-Life PPG Emotion Detection

arXiv:2608. 14675v1 Announce Type: cross Abstract: While Self-Supervised Learning (SSL) effectively extracts general representations from noisy, unconstrained physiological signals such as photoplethysmography (PPG), its suitability for highly subjective tasks remains unproven.

By Dominika Kunc, Przemys{\l}aw Kazienko, Stanis{\l}aw Saganowski

reinforcement-learning fine-tuning

arXiv AI

1d ago

MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems

arXiv:2608. 15006v1 Announce Type: cross Abstract: Although visual reasoning is crucial for solving complex geometry tasks, existing vision-language models rely heavily on text-only reasoning.

By Penghao Yin, Haomin Wang, Qihong Tang, Xiaoye Qu, Hongjie Zhang, Xiao-Ping Zhang

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

1d ago

When to Communicate: Belief Distributions and KL Divergence for Principled Gating in Multi-Agent RL

arXiv:2608. 14559v1 Announce Type: new Abstract: Effective communication in multi-agent reinforcement learning requires agents to decide not only \textit{what} to communicate, but when?

By Teoman Kaman

agents reinforcement-learning benchmarks

arXiv AI

1d ago

Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL

arXiv:2608. 14945v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) gives language agents dense token-level supervision from a privileged self-teacher on the policy's own trajectories.

By Qizhen Lan, Xi Xiao, Xiangchen Guan, Mengchen Fan, Moule Lin, Jung Im Choi, Lijing Zhu

agents reinforcement-learning efficiency

arXiv AI

1d ago

ReasonCast: Agentic Demand Forecasting with Selective Semantic Reasoning

arXiv:2608. 15291v1 Announce Type: new Abstract: Demand forecasting increasingly requires combining two complementary sources of information: historical sales reveal recurring numerical dynamics, while future promotions, holidays, price changes, and platform interventions provide forward-looking knowledge.

By Ziyue Yang, Chaolin Xu, Yijing Wang, Tiankai Gu, Hui Yang, Yanhong Lin, Kaiyuan Liu, Fei Xiao

agents reinforcement-learning fine-tuning

arXiv AI

1d ago

UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms

arXiv:2608. 15372v1 Announce Type: new Abstract: We study generating game-theoretically optimized Courses of Action (COAs) for a Blue UAS swarm against an adaptive Red adversary in a communication-degraded environment, motivated by (but not derived from) a public U.

By Phillip Jiang

agents reinforcement-learning safety

arXiv AI

1d ago

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

arXiv:2608. 15930v1 Announce Type: new Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution.

By Zihan Ding, Longxu Dou, Qi Gao, Xiangwu Guo, Shengchao Hu, Zilong Huang, Zihang Jiang, Lei Ke, Mengcheng Lan, Weixian Lei, Hanxuan Li, Honglin Li, Xiyun Li, Zaitang Li, Leowei Liang, Xin Luo, Haozhe Ma, Jiayi Mao, Zhoujie Pan, Can Qin, Tianyuan Qu, Weiqi Wang, Wenkai Wang, Yonglin Wang, Yuxin Wang, Chenxu Wu, Yingchen Yu, Chenyu Zhang, Yuhao Zheng

agents reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

1d ago

Coverage-Maximizing Multinomial Subset Routing under Operational Constraints

arXiv:2608. 16375v1 Announce Type: cross Abstract: We introduce Multinomial Subset Routing (MSR), a new online routing framework over $K$ experts in which the learner keeps a multinomial routing policy instead of a deterministic subset of experts.

By Quan Zhou, Yiyan Huang

reinforcement-learning