Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, cross-document reasoning at inference time, while precomputed structures like knowledge graphs often fall short because they rely on rigid he...
Anikait Singh, Teresa Zhang, Yoonho Lee et al.· 0 citations
Regularized Recursive Self-Improvement of Agent Harnesses (RRSI) is introduced, which incorporates the principles of regularizations into harness self-improvement by constraining the evolution candidate proposal and selection.
Peng Xia, Ru-Jun Han, Zifeng Wang et al.· 28 citations· ⚡4
This work introduces Stateless Language Agents (SLAs), built on the principle of stateful search with stateless agents, and evaluates SLA against three recent frameworks on software engineering, kernel optimization, and algorithm design at budgets of up to one billion tokens.
Qizheng Zhang, Chang Ji, Isaac Sun et al.· 1 citation
What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-growing archive of research, a new problem needs. To study this skill, we draw on researchers who know firsthand which earlier work advanced t...
Sohyeon Kim, Yoonho Lee, Bo Liu et al.· 0 citations
An LLM agent's capability is largely magnified by its harness, namely the prompts, control flow, tooling, memory, and context management surrounding the frozen backbone model. Recent methods increasingly automate this process by iteratively proposing and selecting component-wise edits of an agent harness, practically e...
Peng Xia, Ru-Jun Han, Zifeng Wang et al.· 3 citations· ⚡1
Weight-Harness Alternating LEarning (WHALE), a simple recipe that alternates two phases: updating the model under the current harness, then searching for a better harness under the updated model with online rejection-sampling fine-tuning and Meta-Harness, is proposed.
Haechan Kim, Yoonho Lee, Gisang Lee et al.· 11 citations· ⚡4
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
