ToolSelf: Runtime Self-Reconfiguration for Robust Long-Horizon Agentic Tasks

Jan 1, 2026·

Jingqi Zhou

Sheng Wang

Co-Corresponding Author

Dezhao Deng

Junwen Lu

Qintong Li

Jiahui Gao

Junwei Su

Hao Wu

Jiyue Jiang

Lingpeng Kong

Chuan Wu

Co-Corresponding Author

· 0 min read

Abstract

ToolSelf introduces runtime self-reconfiguration capabilities for robust long-horizon agentic tasks, enabling agents to adapt their tool usage dynamically.

Type

Preprint

Publication

ICML 2026 Submission

Last updated on Jan 1, 2026

Agent Systems ICML 2026 Submission Co-Corresponding Author

Authors

Jingqi Zhou

Authors

Sheng Wang (Forence)

PhD Graduate in Computer Science

Sheng Wang is a PhD graduate from The University of Hong Kong, supervised by Prof. Chuan Wu and Prof. Lingpeng Kong. His research focuses on Agent, LLM Super-Alignment, and Data Synthesis. He has published 14+ papers in top-tier conferences including NIPS2025 (Spotlight), ICLR2025, ACL2024/2025, EMNLP2025.

Authors

Authors

Authors

Authors

Authors

Authors