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 demonstrates that using Reinforcement Learning from Verifiable Rewards (RLVR) significantly improves small language models' functional correctness in code generation, particularly when combi…

This paper introduces a failure-aware observability framework to diagnose wasted computation in multi-agent LLM systems by mapping recurring failure modes to online trace signals.

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 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…

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

FALAT is a diagnostic framework that treats failure attribution in complex LLM agent trajectories as a dependency-guided search problem, successfully identifying both the responsible agent and the dec…

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…

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

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 Cross-Model Entropy (CME), a novel label-free reward signal that uses an independent verifier model to assess the quality of a generator's output, significantly improving LLM perf…

CARE-RL introduces a framework combining protocol-aware reward generation and capability-aware optimization to effectively mitigate cross-domain conflicts in multi-domain reinforcement learning for LL…

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…

This paper proposes a method to recover recoverability structure from failed traces of post-trained language models, enabling test-time routing and post-training analysis.

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 reframes LLM reliability from an impossible universal problem to a manageable, local patch-based problem, showing that sufficient interventions can be found by focusing on recurring failure…

OccuReward introduces an LLM-guided framework and a Comfort Equity Index (CEI) to shape building energy rewards, demonstrating that iterative refinement significantly improves occupant comfort equity…

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 a logic-driven framework using a neural certificate function to rigorously evaluate and benchmark the generalization capabilities of reinforcement learning algorithms on unseen ta…

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…