Abstract:Recent text-clustering methods use large language models to propose a cluster taxonomy from a corpus and then assign each text to it. These pipelines are fundamentally programmatic: the sequence of LLM calls and the rules for stopping, merging, and splitting clusters are fixed in code in advance, so they generalise poorly across corpora of different structure and cannot easily incorporate user-supplied constraints such as a target cluster count or a clustering intent. We propose an agentic alternative in which an orchestrator LLM inspects the state of the discovery process at each step and dispatches one of a small set of specialised agents - proposer, synthesizer, auditor, investigator, and critic - adapting the pipeline to the corpus rather than executing a fixed one. On seven public text-clustering benchmarks the method achieves state-of-the-art performance, beating the strongest prior LLM baseline by up to 32% in ARI.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2606.01255 [cs.CL] |
| (or arXiv:2606.01255v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.01255 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Emily Silcock [view email]
[v1]
Sun, 31 May 2026 14:18:18 UTC (43 KB)