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

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…

The paper introduces a reinforcement learning framework, inspired by AlphaZero, to automate and improve the proof search process within the Tamarin protocol analysis tool, resulting in shorter and mor…

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 introduces Sefz, a semantic fuzzing framework that automatically discovers specification violations in LLM agent skills, finding a significant number of previously unknown exploitable guardr…

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

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…

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

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 agentic fuzzing, a novel bug-finding approach where deep agents perform direct reasoning based on historical bugs to discover logic bugs in mature codebases.

The paper introduces BenchJack, an automated red-teaming system that systematically audits popular AI agent benchmarks, revealing numerous reward-hacking exploits and demonstrating a method to signifi…

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial…

The paper proposes a two-stage post-training pipeline to create a small, local LLM agent (PrivEsc-LLM) capable of performing Linux privilege escalation, achieving high success rates while drastically…

SDLLMFuzz is a novel dynamic-static framework that combines LLM-based structure-aware input generation with semantic feedback from crash analysis to significantly improve vulnerability discovery in st…

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…