Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configured organizations are followed faithfully, whereas reality differs. This behavioral gap, combined with differences in underlying system components, prevents c...
Chun-Wah Hsu, Kai Gong, Yu Wu et al.· 1 citation· ⚡1
An empirical study of router-side injection in coding agents, examining four intervention levels of increasing subtlety and developing SIDEL, a framework for trace recording, replay, injection, and defense evaluation, which is evaluated four representative coding agents, and further evaluates whitelist-based execution...
Donghao Fu, Jingxin Li, Xue Jiang et al.· 0 citations
Adaptive Reuse of Cached Hidden States for Efficient Rollback (Archer) is introduced, a training-free KV caching method for rollback-capable DLMs that characterizes prompt reuse as a reversibility-aligned cache boundary, bounds its state-dependent approximation error, and gives a decoder-margin condition for preserving...
Xuning He, Zinan Sheng, Yong-Ding Tao et al.· 1 citation· ⚡1
PRAXIS is a framework that enables agents to systematically extract, represent, and reuse tacit knowledge for domain code generation and outperforms state-of-the-art agents equipped with powerful agentic search capabilities, as well as experience-based and skill-based methods.
Xue Jiang, Tianyue H. Zhang, Ling-Wei Wu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
