We have 5 of 18 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Reinforcement learning with a verifiable reward (RLVR) offers a scalable approach to training language-model agents, yet sparse outcome rewards can leave early training with little signal for policy improvement. We identify an On-Policy Acceleration Phenomenon: in our main comparisons, RLVR initialized with on-policy d...
Safety alignment of large reasoning models (LRMs) via supervised fine-tuning (SFT) and reinforcement learning (RL) often yields near-perfect safety scores, yet this apparent success comes at the cost of severe over-refusal and degraded general capabilities. Through systematic empirical analysis, we find that these fail...
SALA is proposed, a Semantic-Aware Logical Alignment framework that automatically learns task-specific reasoning operations and uses dynamic time warping to align the reasoning sequences.
A conflict-driven preference optimization framework for model merging (CoMerge), which reformulates model merging as a preference optimization problem and utilizes a self-supervised, conflict-driven strategy that leverages the defects of naive merging methods as hard negative samples to construct preference pairs witho...
This work introduces AgentSnare, a trajectory-adaptive deception system that dynamically unfolds a decoy environment to continually steer the penetration agent away from the real target.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
