It is indicated that current coding agents cannot yet reliably reason about execution in complex systems codebases, and that paired evaluation is necessary to measure this ability.
Chen-Xi Huang, Hao-Nan Wang, Jing-He Zhang et al.· 0 citations
Test-time search can improve agent performance by exploring alternative actions and using a critic to select promising branches. We study this approach in terminal-based computer-use environments, which expose only a partial view of a large underlying state, and find that the Monte Carlo tree search (MCTS) configuratio...
Jia-Kai Xu, Tian-Cheng Ge, Tu-Jie Guan et al.· 0 citations
AI agents improve task success by exploring multiple trajectories, but for computer-use agents each trajectory modifies external environment state. Branching from an intermediate point is correct only when restoration is observation-equivalent - future actions produce the same observations - and practical only when cre...
Jia-Kai Xu, Tian-Le Zhou, Georgios Liargkovas et al.· 0 citations
Modern web applications are typically implemented by many independent microservices. Seeing into such a distributed system and predicting how component changes propagate across the system is essential for informed decision-making. Unfortunately, existing tools provide only partial support for such analysis in microserv...
Meghna Pancholi, Lee Baugh, Olaf Schnapauff et al.· Conference on Applications,...· 0 citations
Online OS tuning can improve long-running services, but existing tuners are not well suited for live hosts. They treat scheduler, power, memory, and I/O controls as black-box variables and optimize a scalar reward. This approach ignores cross-knob policy structure, breaks down when application metrics are unavailable,...
Georgios Liargkovas, M. Joshi, Hubertus Franke et al.· Proceedings of the ACM SIGOP...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.