CRITIC-R1 introduces a structured critic framework that treats RAG critique as an explicit error diagnosis problem using reinforcement learning, significantly improving answer quality over strong RAG…

The paper introduces a diagnostic benchmark for selective Question Answering over conflicting, multi-source personal memory, demonstrating that specialized fusion resolvers outperform general LLMs, es…

SCOPE introduces a data-free self-play framework that co-evolves a task-generating Challenger and a document-answering Solver, significantly improving open-ended performance on language models without…

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in…

The paper proposes Hysteretic Policy Optimization (HPO) and its adaptive variant (A-HPO) to stabilize reinforcement learning training in sparse-reward environments by better balancing positive and neg…

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 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…

The paper addresses the 'detection-to-abstention gap' in reasoning models, where detecting insufficient information does not lead to abstention, by proposing a novel control framework that forces mode…

The paper proposes Shapley-based input uncertainty Quantification (ShaQ), a novel framework that uses Shapley values to precisely attribute input-induced uncertainty to specific spans of text, providi…

HMPO introduces a single-stage, cost-effective reinforcement learning framework that achieves significant token compression of Chain-of-Thought reasoning with minimal loss of accuracy, applicable acro…

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…

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…

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…

This paper investigates the non-monotonic role of sample difficulty in Reinforcement Learning with Verifiable Reward (RLVR), finding that medium-difficulty problems provide the most balanced and benef…

Critic-R introduces a novel framework that uses a critic model to provide natural language introspective feedback, significantly improving the performance of agentic search systems by optimizing retri…

The OISD framework improves language model reasoning by distilling on-policy predictive signals from the final output layer to intermediate representations, leading to substantial improvements on math…

The paper introduces Posterior Hybrid Bayesian Belief (PhyB), a novel framework that reformulates policy optimization in Bayesian Offline RL by approximating expectations as a convex combination over…

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

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