ARCHITECT: Uncertainty-Aware Dynamic Tool Learning via Causal Intervention for Open-World Agents

Zhangyi Wang, Jiexiang Xu, Bingnan Yu, Zongze Li


Abstract
Dynamic tool generation empowers Large Language Model (LLM) agents to synthesize tools on demand, yet a critical challenge remains: 32.4% of generated tools fail on first invocation. We present Causal Tool Diagnosis (CTD), a principled framework that moves beyond black-box reliability prediction to interpretable failure attribution. CTD constructs a Structural Causal Model (SCM) capturing how specification quality, code characteristics, and execution environment jointly determine tool outcomes. Uniquely leveraging code’s intervenability, we conduct controlled sandbox experiments to estimate causal effects—an advantage unavailable in pure text generation. CTD jointly predicts confidence (Spearman rank correlation coefficient 𝜌=0.90) and root cause attribution (78% accuracy), with attributions directly guiding targeted repairs (+9.6% success rate over error-type classification). Our ARCHITECT framework, integrating CTD throughout the tool lifecycle, achieves state-of-the-art on four benchmarks including StableToolBench (+3.8%), MINT (+4.6%), T-Eval (+3.7%), and SWE-bench Lite (+2.4%), with consistent improvements across all settings.
Anthology ID:
2026.acl-long.1707
Volume:
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
36819–36829
Language:
URL:
https://aclanthology.org/2026.acl-long.1707/
DOI:
10.18653/v1/2026.acl-long.1707
Bibkey:
Cite (ACL):
Zhangyi Wang, Jiexiang Xu, Bingnan Yu, and Zongze Li. 2026. ARCHITECT: Uncertainty-Aware Dynamic Tool Learning via Causal Intervention for Open-World Agents. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 36819–36829, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
ARCHITECT: Uncertainty-Aware Dynamic Tool Learning via Causal Intervention for Open-World Agents (Wang et al., ACL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.acl-long.1707.pdf
Checklist:
 2026.acl-long.1707.checklist.pdf