The paper proposes ProRL, an effective Reinforcement Learning framework that rectifies gradient estimation deficiencies to optimize proactive recommendation paths, significantly outperforming existing…

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 LearnWeak, an annotation-free framework that automatically specializes small computer-use agents by identifying and targeting their specific weaknesses using a stronger reference…

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…

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…

This paper proposes a new imitation learning algorithm called DistIL that uses distributional feedback to improve policy improvement and regret guarantees.

The paper proposes RoRo, a rubric-guided process reward framework that improves stepwise model routing by evaluating the quality of intermediate reasoning steps, leading to better performance and cost…

The paper proposes Multi-Agent Computer Use (MACU) systems, which significantly improve performance on complex, long-horizon tasks by enabling parallel execution and dynamic task decomposition compare…

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…

This paper proposes a new method for agentic Reinforcement Learning called Agentic Procedural Policy Optimization (APPO) that improves tool-use capabilities by assigning credit to fine-grained decisio…

This paper demonstrates that a complex deep reinforcement learning policy for power grid control can be successfully distilled into a lightweight, auditable decision tree and random forest surrogate t…

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional m…

VLA-Pro is a plug-and-play framework that enhances cross-task generalization in Vision-Language-Action models by storing and dynamically retrieving task-specific procedural memories, achieving signifi…

EchoRL proposes a lightweight module to exploit valuable learning signals from advantage-degenerated rollouts in Reinforcement Learning with Verifiable Rewards (RLVR), significantly improving LLM post…

The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.

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 Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals…

The paper introduces Safe Equilibrium Policy Optimization (σepo{}) to train language models for multi-agent strategic tasks, achieving improved safety and robustness across various game domains.

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

SelSkill introduces a dual-granularity preference learning framework that treats skill use as a 'skill-or-skip' decision, significantly improving agent performance and execution precision in complex a…