PRO-CUA introduces a process-reward optimization framework that enables efficient, step-level reinforcement learning for training computer use agents by decoupling environment interaction from policy…

ESPO is a novel reinforcement learning algorithm that detects trajectory failure in large language models and terminates rollouts early, significantly improving performance on mathematical reasoning b…

Taiji is a novel LLM-as-Enhancer framework that optimizes recommender systems by addressing the challenges of generating high-quality reasoning data and balancing semantic and ID-based rewards.

The paper introduces the Markov decision contest, a new framework for reinforcement learning using pairwise preferences, and proves that stationary Markov policies are optimal and solvable efficiently…

The paper advocates for integrating explicit contextual feedback (like reviews and comments) into LLM-based recommender systems to achieve more personalized, transparent, and semantically aligned reco…

The paper introduces Graph-Distance Contribution Reward (GDCR) and Step Advantage Policy Optimization (SAPO) to provide fine-grained, step-level credit assignment for agentic search by modeling world…

The paper introduces local Preferential Bayesian Optimization (PBO) methods that adapt high-dimensional Bayesian Optimization techniques, such as trust-region and derivative-informed local search, to…

The paper introduces PARL, a framework that learns personalized evaluation rubrics directly from raw user interaction histories to accurately assess how well LLM outputs align with subjective, user-sp…

The paper proposes SAAS, a novel RL framework that equips LLM agents with self-awareness to precisely regulate search behavior, significantly mitigating costly over-search without sacrificing accuracy…

The paper introduces Prompted Policy Optimization (PromptPO), an LLM-based method that successfully optimizes policies for various sequential RL tasks, demonstrating that LLMs can replace classical RL…

The paper introduces a quotient-DAG view to accurately estimate unordered slate propensities for off-policy evaluation, solving the nuisance variance and computational gap inherent in standard importa…

This paper analyzes Best-of-$N$ preference data, deriving explicit reward targets for independent-reference variants and establishing design principles for choosing $N$ and the base distribution to op…

SPADER is a novel reinforcement learning framework that addresses the challenges of Multi-Answer Question Answering by improving credit assignment and promoting diverse exploration during long-horizon…

The paper introduces 'reward bias substitution,' demonstrating that single-axis mitigations of reward model biases merely shift optimization pressure to correlated proxies, and proposes augmenting eva…

The paper introduces SAVE, a framework that uses on-policy feedback and the value function to self-supervise and improve reward models, significantly enhancing RLHF performance across multiple benchma…

The paper proposes Credit-Attenuated Privileged Feedback (CAPF), a training-time mechanism that uses verifier-side information to guide LLM search agents, significantly improving their performance on…

The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…

The paper introduces OpenWebRL, an open framework that enables training visual web agents using online multi-turn Reinforcement Learning directly on live websites, achieving state-of-the-art performan…

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training a…