Story
arxiv_cs_ai · Sep 22, 2026 · paper
Source brief
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
arxiv.orgSep 22, 2026
original source linked
In brief
Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same control decisions inside each task's context. We study whether task feed...
Feed lens
agentharness