A more challenging and realistic benchmark, BUILD-BENCH, comprising OSS that is more diverse in quality, scale, and characteristics is proposed, and a strong baseline LLM-based agent, OSS-BUILD-AGENT, an effective system with enhanced build instruction retrieval module that achieves state-of-the-art performance on BUIL...
Ze-Hua Zhang, Ati Priya Bajaj, Divij Handa et al.· arXiv.org· 2 citations
A multi-agent harness that represents each request as a persistent, artifact-grounded analysis run, and demonstrates that reliable bioinformatics automation depends not only on model capability, but also on the harness that governs planning, execution, memory, and evidence flow.
Qi Shao, Xin Zhang, Zhou-Yang Yuan et al.· 0 citations
It is argued that a lifelong AI partner for materials science can be designed around persistent memory rather than around a particular agent implementation, and a self-evolving memory framework is introduced that stores scientific experience as inspectable facts and executable skills so that observations, failure bound...
Si-Yu Liu, Bo Hu, Beilin Ye 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.
