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…

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.

This paper demonstrates that transformer-based policies can provably learn complex tree search mechanisms, such as depth-first search, purely through reinforcement learning in a stochastic environment…

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

The paper proposes ReuseRL, a method that improves agent generalization in Reinforcement Learning by enforcing structural compressibility of successful agent trajectories into reusable skills.

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…

ReSkill is an RL-in-the-loop framework that reconciles skill creation and policy optimization by automatically creating, testing, and refining modular skills alongside the agent's policy learning, lea…

The paper introduces AgenticRL, a self-refining reinforcement learning framework that uses a multimodal GPT agent to automatically design, refine, and deploy reward functions for complex UAV navigatio…

The paper proposes a modular agent framework and novel learning methods to design and optimize practical, cost-effective, and controllable LLM-based agentic systems.

This paper develops a policy-learning framework to optimally assign prediction tasks to multiple agents, considering individual agent expertise and capacity constraints, achieving systematic performan…

This paper analyzes tool-calling in LLM agents, demonstrating that evaluation results are highly sensitive to implementation details and proposing new techniques to significantly improve the efficienc…

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…

This paper synthesizes expert knowledge from a workshop to provide a comprehensive framework and best-practice guidelines for developing high-quality reinforcement learning environments for autonomous…

The paper proposes a scalable, distributed approach for constrained Multi-Agent Reinforcement Learning by using local consensus over dual variables to ensure global constraint satisfaction without cen…

The paper introduces PTCG-Bench, a new benchmark using the Pokémon TCG to evaluate LLM agents' strategic decision-making and ability to self-evolve, finding that sustained self-evolution remains chall…

The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to impr…

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 proposes a Network Distributed Multi-Agent Reinforcement Learning (ND-MARL) framework that enables stable, scalable consensus control for large swarms of quadcopters using only local neighbo…

The paper develops an optimistic maximum-likelihood algorithm that achieves $ ilde{O}(\sqrt{T})$ policy regret for sequential decision-making in partially observable Markov games against adaptive oppo…

The paper proposes extending world models for multi-agent reinforcement learning by factorizing the latent state to explicitly model and predict the unobservable intentions and behaviors of teammates.