UChicago FoH 框架：分布式多智能体推理中 server 同时进化 client 与自身 harness，提升 53.57% / 29.76%

View PDF HTML (experimental)

Abstract:Modern LLM-powered agents increasingly improve through experience sharing, where distributed agents distill local reasoning experience into reusable knowledge, such as a shared insight library. Existing approaches, however, still heavily rely on manually designed prompts and workflows that determine both how local agents extract useful reasoning traces and how a central/global agent aggregates them to obtain common patterns and insights. We propose Federation over Harness (FoH), a framework that automatically evolves the harness for both local and global components in this distributed multi-agent reasoning pipeline. A server agent evolves the client harness for task solving and self-reflection while, at the same time, evolving its own harness for aggregating distributed reflections, maintaining shared knowledge, and updating subsequent client harnesses. Importantly, FoH requires no extra validation signals, such as ground-truth labels or validation data, during evolution; it learns solely from self-generated reflections produced by distributed agents. Experiments on multiple benchmarks show that FoH consistently improves over single-agent baselines with a fixed harness and with harness self-evolution by 53.57% and 29.76%.

Submission history

From: Dixi Yao [view email]
[v1] Thu, 15 Oct 2026 19:34:45 UTC (236 KB)