知识图谱即文件：工具创建与工具使用协同演化的 Agent Harness

View PDF HTML (experimental)

Abstract:Searching text-rich knowledge graphs requires following relations while examining textual evidence. Predefined graph interfaces constrain what evidence agents can access, even when they write code to combine tool calls or process retrieved subgraphs. We propose direct knowledge graph interaction (DKGI), a harness in which language model agents create graph access tools directly over complete node and edge files. The agent writes Python code to follow relations, combine node sets, and select textual evidence, interleaving execution with shell search and file inspection. This lets agents process large node sets in bulk while returning selected text for the model to assess. Execution feedback guides tool creation and revision, while the evolving tools determine what evidence the agent gathers next. On benchmark datasets spanning three domains, training-free DKGI exceeds the strongest published baseline by at least 6.7 Hit@1 points on every graph, even with a minimal harness. Controlled ablations show the benefits of multi-turn programming over shell-only access and predefined graph tools, while trajectories show agents revising code to extend searches or address errors. These findings highlight the value of allowing tool creation and tool use to co-evolve during graph search. Our code and data are available at this https URL.

Comments:	27 pages. Code and data: this https URL
Subjects:	Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
Cite as:	arXiv:2610.18616 [cs.CL]
	(or arXiv:2610.18616v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.18616 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yuyang Bai [view email]
[v1] Tue, 13 Oct 2026 16:00:50 UTC (359 KB)