cs.CLNov 10, 2026

Synapse-Control: Making Agent Experience Actionable with Lightweight Runtime Control

Authors: Zhiyuan Huang, Shengan Zheng, Chenghu Yang, Song Zhang, Lingyun Li, Chen Yu, Weiquan Huang, Linpeng Huang

Organizations: Shanghai Jiao Tong University Shanghai, China · Ant Group Hangzhou, China · MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University Shanghai, China

Abstract

Large language model agents reuse execution experience to improve reliability on complex tool-based tasks. Systems such as Sentry call large models to generate failure diagnoses before retrieving advice, adding inference cost to experience reuse. We present Synapse-Control, an agent runtime whose lightweight control plane selects advice and determines when to send it to the task-executing model. Rules shortlist relevant advice, and a lightweight 1.7B classifier fine-tuned on teacher-labeled state-suggestion pairs scores those candidates instead of generating a diagnosis. Micro-contracts encode reusable interface checks, such as required arguments or valid options, without prescribing complete task programs. A Prompt Value Table records earlier guidance and feedback to limit repeated suggestions through cooldown and token-budget checks. Across 1,308 attempts per method in AppWorld and WebShop, Synapse-Control achieves 270 successes (29.8% more than Base), replaces 4,987 generative diagnosis calls, and reduces auxiliary control time relative to Sentry by 50.2% and 51.0%, respectively.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents

    Sep 22, 2026Laizhen Li, Jiarui Li, Juanjuan Zhao +4Agent Harness OptimizationLLM Agent Workflow Optimization

  2. Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making

    Jul 15, 2026Amirhosein Ghasemabadi, Ruichen Chen, Bahador Rashidi +1Multi-Agent LLM SystemsLanguage Model-Based Control

  3. ReGE: Stronger Agents through Experience Synthesis

    Oct 24, 2026Jiarong Liang, Yubo Wang, Zijie Liu +3Experience Learning for LLM AgentsLLM Agent Self-Improvement