This paper introduces RREDCoT, a method for approximating optimal reward redistribution in Chain-of-Thought reasoning language models without additional generation.

This paper proposes TRIAGE, a role-typed credit assignment framework for agentic reinforcement learning to address the structural incompleteness of standard GRPO.

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…

The paper proposes a novel temporal and structural credit assignment framework to efficiently optimize multi-agent LLM systems by decomposing the error signal and using targeted, discrete gradient upd…

This paper proposes a framework for reward allocation in AI cooperatives using value-conditioned gradient filtering, online marginal contribution signals, and cumulative revenue settlement within a tr…

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 introduces the concepts of Agentic Technical Debt and Stochastic Tax to categorize and manage the unique governance and operating liabilities inherent in complex, multi-step AI agent systems…

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…

SkillC introduces a Contrastive Skill Credit Assignment (CSCA) framework to enable LLM agents to autonomously internalize skills during training, significantly outperforming existing methods without r…

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…

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 ARCA, a novel credit assignment method that measures token salience directly from the adapter's residual hidden state, addressing the degeneracy of standard intrinsic signals when…

This paper introduces mean field reinforcement learning through Markov decision processes in large-population stochastic control, developing the necessary framework for representative-agent learning,…

The paper proposes a Hierarchical Reinforcement Learning framework with two levels for handling high-level strategic planning and low-level continuous-control using Soft Actor-Critic and entropy-regul…

TRACER introduces a novel turn-level reinforcement framework that enables cooperative multi-LLM reasoning by separating decision-making into a regret-matching controller and a generation-credit layer.

This paper provides a mathematical framework for studying different policy learning problems and shows reductions between them.

This paper rigorously proves that a Reinforcement Learning Hyper-heuristic (RLHH) optimizes the LeadingOnes benchmark function with optimal expected runtime using two random local search operators, ou…