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

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 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 Aethelgard, a novel four-layer adaptive governance framework that enforces least privilege by learning the minimum necessary capabilities for autonomous AI agents based on their i…

The paper introduces a novel shielding framework for Robust MDPs (RMDPs) that guarantees safety under worst-case transition probabilities, enabling safe reinforcement learning even when transition dyn…

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

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 the Configurable Safety Reward Model (CSRM), a novel reward model that can be jointly optimized for calibrated safety compliance and reward modeling, significantly improving LLM s…

SafeMCP is a server-side defense plugin that uses look-ahead reasoning to proactively filter and constrain tool acquisition for LLM agents, thereby mitigating catastrophic risks associated with expand…

This paper introduces Capability Self-Assessment (CSA), a crucial ability for LLMs to recognize their limitations, and demonstrates that reinforcement learning is an effective method for teaching this…

The paper proposes a two-timescale governance framework using a multi-agent LLM to safely update and guide RL agents for SDN-IoT defense, significantly improving performance and stability under advers…

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 Safe Equilibrium Policy Optimization (σepo{}) to train language models for multi-agent strategic tasks, achieving improved safety and robustness across various game domains.

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…

The paper proposes the Policy-Execution-Authorization (PEA) architecture, a separation-of-powers system designed to structurally enforce goal integrity in AI agents, moving safety from a probabilistic…

The paper proposes a local perturbation theory showing that cross-domain interference in multi-domain RL occurs via a low-dimensional shared conflict subspace, which can be selectively mitigated by sh…