PRefine：面向多会话个性化工具调用的潜在偏好建模

View PDF HTML (experimental)

Abstract:Users often omit essential details in their requests to LLM-based agents, resulting in under-specified inputs for tool use. This poses a fundamental challenge for tool-augmented agents, as API execution typically requires complete arguments, highlighting the need for personalized tool calling. To study this problem, we present Multi-Session Personalized Tool Calling (MPT), a benchmark comprising 4,695 instances over 459 multi-session interaction histories that cover three challenges: Preference Recall, Induction, and Transfer. We further propose PRefine, a test-time memory method that maintains the user's latent preference as a textual hypothesis revised through a generate--verify--refine loop. Across five LLMs, existing memory systems often fail to improve on full-history prompting; PRefine outperforms all baselines and alone surpasses it on Preference Transfer. These results indicate that memory for personalized agents must abstract behavior into preferences, rather than simply archive it.

Comments:	Under review. 27 pages, 14 figures, 19 tables. v2: revised benchmark construction and extended analysis
Subjects:	Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2604.17886 [cs.CL]
	(or arXiv:2604.17886v3 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2604.17886 arXiv-issued DOI via DataCite

Submission history

From: Yejin Yoon [view email]
[v1] Mon, 20 Apr 2026 06:57:50 UTC (1,354 KB)
[v2] Tue, 8 Sep 2026 09:54:31 UTC (2,273 KB)
[v3] Wed, 14 Oct 2026 13:27:25 UTC (2,359 KB)