A unified theory for RE(S) is developed that covers the full spectrum of S, and can be interpreted as a stage-wise optimization process, where each stage takes $S$ gradient steps for minimizing the Kullback-Leibler distance to a fixed reward-weighted rollout distribution.
Zhi-Wei Wang, Yan-Xi Chen, Ya-Liang Li et al.· 0 citations
Real-generation experiments that account for the pilot synchronization barrier show that HBN-async mitigates its overhead, helping translate statistical efficiency into practical evaluation benefits, and outperforming hindsight-tuned empirical and independent Bayesian baselines.
Qian-Li Shen, Xiang Li, Ruo-Meng Ding et al.· 0 citations
This paper formalizes preference privacy, a label-DP-style privacy notion for DPO that protects only the relative preference between candidate responses, assuming an adversary who already knows the prompt and responses, and designs PrivDPO, a DPO variant that enforces preference privacy while remaining compatible with...
Yang-Fan Jiang, Fei Wei, Ergute Bao et al.· 0 citations
TrajVal, a lightweight probe-based estimator that approximates per-task learnability from a short probe run and two endpoint evaluations, is proposed and it is found that learnability is reproducible across independently sampled training contexts and predictive of downstream utility.
Ting Zhou, Zhenqing Ling, Daoyuan Chen et al.· 0 citations
MTGuard is proposed, a hybrid analysis-based defense framework designed to safeguard the use of MCP tools in LLM agents by leveraging lifecycle-aware static-dynamic co-analysis and effectively mitigates multiple categories of harmful tool use across different LLM agents while maintaining performance on benign user task...
Ping He, Yuexiang Xie, Yaliang Li et al.· arXiv.org· 0 citations
EvoSOP is introduced, a framework that empowers agents to extract SOPs from execution trajectories and iteratively optimize the toolset through a systematic lifecycle of construction, merging, evaluation, and pruning, providing a scalable pathway for the development of self-evolving agents.
Haipeng Ding, Yuexiang Xie, Zhewei Wei et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.