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…

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…

The paper proposes using an LLM aggregator that analyzes complete reasoning traces, demonstrating that trace-level synthesis is superior to traditional consensus methods like majority voting for solvi…

This paper investigates if team-based interaction improves LLM performance on complex reasoning tasks (ChGK), finding that structured team strategies significantly boost accuracy by acting as error-fi…

The paper introduces Mindgames, a comprehensive multi-game arena for evaluating LLM agents' sustained social and strategic reasoning, demonstrating that current evaluations are limited by structural s…

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…

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 JAMEL framework addresses the challenge of effective exploration in open-ended environments by jointly training agent memory and exploration policies using natural, novelty-driven signals.

The paper introduces Latent Reward Steering (LRS), an adaptive inference-time framework that implicitly improves the reasoning ability of LLMs by guiding the model's internal latent states based on a…

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…

LongTraceRL addresses long-context reasoning challenges by generating highly challenging training data and introducing a fine-grained rubric reward, significantly improving evidence-grounded reasoning…

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, sign…

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 AGENTCL, a rigorous evaluation framework that uses controlled task streams to accurately measure an agent's ability to accumulate and reuse knowledge across multiple tasks, thereb…

ExpGraph is a model-agnostic framework that uses a self-evolving experience graph to enable LLM agents to reuse past successful strategies and failure lessons, significantly improving performance acro…

The paper investigates how LLMs allocate their internal computational depth during multi-turn agentic planning, finding that agents progressively recruit deeper layers and shift toward corrective upda…

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

TraceGraph introduces a graph-based framework to map agent decision-making across pooled trajectories, revealing hidden differences in agent behavior and improving performance by targeting known failu…

This paper introduces MCTS-Guided Group Relative Policy Optimization (M-GRPO) to enhance LLM spatial reasoning by improving the decomposition of complex tasks into optimal sub-tasks.

The paper introduces TRACE, a novel metric that evaluates the logical structure of LLM reasoning (CoT) by integrating Toulmin's argumentation theory, demonstrating that sound reasoning structure corre…