Roles in multi-agent large language model (LLM) systems allocate decisions as well as work. In a Planner--Executor--Reviewer team, the Reviewer's approval can determine when the team submits an answer and receives corrective feedback. We study both functions by varying role instructions while holding agents, topology,...
Chih-Hsuan Yang, Xin-Yan Li, Rajeev Thakur et al.· 0 citations
Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test t...
Chih-Hsuan Yang, Anjir Ahmed Chowdhury, Cheng-Hau Yang et al.· 2 citations
LAM is proposed, a Lossy Agent Memory system with three components: a deterministic deduplication rule with a substitution bound on retrieval scores - a bound on score perturbation, not a certificate of unchanged ranking; a memory manager that preserves the cached prefix and overlaps compaction with inference; and a pe...
Bai-Xi Sun, Le Chen, Anjir Ahmed Chowdhury et al.· 0 citations
The transferable lesson is procedural: routing discrimination, probability calibration, and public commitment must be measured separately before raw confidence is used for deployment decisions.
Jingyan Jiang, Hui-Huo Zheng, Rajeev Thakur et al.· 0 citations
This work focuses on semantic heterogeneity and studies how it should shape the management and evaluation of working memory in coding agents, finding that semantically different working-memory objects exhibit distinct retention and compression behavior.
Le Chen, Zi-Shen Wan, Bai-Xi Sun et al.· 1 citation
Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collaboration is worth its cost, so confidence can support initial escalation, while protocol-specific cost-aware routing remains unresolved.
Chih-Hsuan Yang, Jingyan Jiang, Cheng-Hau Yang 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.