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

The paper proposes Skill-Conditioned Gated Self-Distillation (SGSD), a novel framework that uses retrieved, potentially noisy skills to guide LLM reasoning, achieving state-of-the-art performance on m…

The paper introduces TRON, an online, rule-verifiable environment substrate that generates an unbounded stream of fresh, controllable visual reasoning training instances, significantly improving RL pe…

The paper analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…

The paper proposes CAST, an answer-free self-distillation method that enhances Group Relative Policy Optimization (GRPO) for verifiable rewards, allowing token-level advantage signals even when all sa…

The paper introduces $ ext{RLR}^3$, a novel framework that extends verifiable rewards in Reinforcement Learning to handle partially verifiable, multi-criteria vision-language tasks by integrating robu…

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 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 Feedback Distillation, a novel training method that uses a language model's privileged feedback to provide token-level supervision, significantly improving complex reasoning tasks…

FineVerify introduces a fine-grained self-verification framework that improves agentic search by decomposing complex questions into verifiable sub-questions, leading to significant accuracy gains over…

The paper introduces OmniVerifier-M1, a multimodal meta-verifier that uses symbolic outputs and decoupled reinforcement learning to provide robust, fine-grained verification and error localization for…

The paper introduces FormInv, a measurement protocol that reveals significant semantic inconsistencies in existing mathematical reasoning benchmarks, showing that standard accuracy metrics fail to cap…

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…

The paper introduces COVCAL, a risk-controlled method that precisely determines when a partial formalization signal from an autoformalizer can be trusted to certify the correctness of natural-language…

The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…

This paper introduces a novel backdoor attack (ACB) against Reinforcement Learning with Verifiable Rewards (RLVR), demonstrating that poisoning the training data can implant a backdoor that significan…

KVerus is a retrieval-augmented system that significantly improves the scalability and resilience of formal verification for Rust code by managing complex cross-module dependencies and adapting to cod…

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 introduces FVSpec, a large-scale benchmark that translates thousands of real-world Python property-based tests into formal Lean 4 specifications to evaluate AI models for formal software ver…