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 introduces a verifier-fuzzing framework to detect and analyze failure modes in Reinforcement Learning with Verifiable Rewards (RLVR) where bugs in the reward verifier can be exploited by the…

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…

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…

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

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 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…

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 Atomic Decomposition and Recombination (ADR), a novel framework that generates genuinely novel and challenging verifiable code tasks, significantly improving the scalability of Re…

This paper introduces CHERRL, a controllable hacking environment for rubric-based reinforcement learning to study and mitigate reward hacking.

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

The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.

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 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 REFT, a novel method that diversifies rollouts by sampling the first token after the reasoning marker, significantly improving performance in Reinforcement Learning with Verifiabl…

IRDS introduces a novel data selection method that uses a verifier-coupled sparse autoencoder framework to efficiently select high-quality Reinforcement Learning with Verifiable Rewards (RLVR) trainin…

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 introduces EASE, a method that enhances multimodal Reinforcement Learning with Verifiable Rewards (RLVR) by providing spatial attention supervision anchored to visual evidence, significantly…

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…