On-policy distillation (OPD) has recently emerged as a promising approach for transferring the capabilities of large agents to compact students. In deep search, where agents iteratively retrieve external evidence, a teacher's preference among plausible queries before retrieval may not predict which queries will return...
Chen-Xi Li, Xue-Yang Feng, Song-Yang Liu et al.· 0 citations
Novels tell rich stories, but their textual form cannot directly present the sights and sounds of the worlds they describe. Film adaptations offer an audiovisual experience but require substantial production effort and viewing time; film recaps are shorter but depend on existing footage. Neither route directly provides...
Kyrie You Wu, Chao-Zhuo Li, Song-Yang Liu et al.· 0 citations
This paper introduces AgentSafeEvo, a co-evolutionary reinforcement learning framework for agent safety built on an attacker-defender game spanning diverse tasks and attack types, and introduces learnability-guided task weighting, which uses within-task defender-reward variability to adjust each task's contribution to...
Chen-Xu Wang, Xiaoyu Wen, Han Qi et al.· 0 citations
A holistic framework based on learnable information gain, which measures how much novel, parameterizable information a round provides relative to the previous round, and proposes ATRI (Adaptive Training Regulation via Information-gain), which reweights samples within a round and halts training across rounds when inform...
Chen-Xu Wang, Chao-Zhuo Li, Xin-Ze Shi et al.· arXiv.org· 0 citations
This work introduces \textsc{JailbreakSkill}, a skill-centric framework for scaling automated red-teaming through reusable and continuously evolving attack capabilities, which packages existing attack strategies into modular, agent-ready skills that can be directly reused and adaptively selected across tasks and target...
Xiaoyu Wen, Jiajia Li, Zhida He et al.· 2 citations
STAR—Staged Training with Aligned Reinforcement Learning and Multi-Faceted Distillation is proposed, a progressive framework that follows a reasoning, ranking, and transfer pipeline to imbue dense models with both high performance and interpretability.
Chenxu Wang, Jianzhi Shao, Chi Zhang et al.· Annual International ACM SIG...· 0 citations
The proposed TRACE (Term-level Reasoning And Chain-of-thought Enhanced distillation), a framework designed for deploying advanced reasoning capabilities at scale, enhances an LLM's multi-modal reasoning by employing Group Relative Policy Optimization (GRPO) guided by a term-level Chain-of-Thought (CoT) reward function,...
Chenxu Wang, Chi Zhang, Fang liang et al.· Annual International ACM SIG...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.