Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache memory binds. Many such systems add a persistent tier storing and recalling reasoning traces, usually validated by an ablation reporting an accuracy gain. We measure b...
Ho-Chan Son, Kyungdoe Han, Jaehan Koh et al.· 0 citations
LLM agents for clinical text-to-SQL applications reason autonomously over multiple steps but cannot assess whether their own reasoning or outputs can be trusted. In high leverage applications such as healthcare, this presents a critical risk where system mistakes can be costly. These reliability failures are also resou...
Mincheol Daniel Song, Joshua Ward, Jake Jung et al.· 0 citations
CyberProvenance is proposed, an agent cyber harness designed for multi-agents that augments LLM agents with evidence accumulation, execution-based validation, and feedback-guided refinement mechanisms for reliable attack-chain provenance.
Qi Chen, Fu-Shuo Huo, Hang-Li Shen et al.· 0 citations
FinInteract, a bilingual (English/Chinese) benchmark of 173 instances that pairs each question with a default and an intended interpretation across a five-category ambiguity taxonomy, and grades whether an agent elicits the right clarification and then integrates it, finds that conditioning on the ambiguity category im...
Xin-Yu Wang, Tung Sum Thomas Kwok, Zhenghan Tai 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.
