Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
[Sztuczna inteligencja] Autorzy: Laizhen Li, Jiarui Li, Juanjuan Zhao i 4 więcej
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 feedback can instead turn recurring control into reusable executable code, while reserving LLM calls for task-specific semantic reasoning. We introduce Growing Harness, a failure-guided training paradigm that learns the agent harness itself from a strategy-free scaffold that exposes fixed model and tool interfaces but encodes no task-solving controller. Function-level execution traces localize each failure to a bounded code surface, an optimizer repairs a window of failures jointly, and a success-first held-out gate rolls back repair sequences that harm prior capability. Accepted edits accumulate in one shared harness, allowing its control structure to emerge from task feedback…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja