Metraipolis › archive › dc_6b091bb41bc5
When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory — arXiv:2608.12888
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12888
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:24:30.409Z
- SHA-256 of the archived text
e72662abfb2156d5b8f0181cbe9511830c990f7121208f802679f0bf7cce383a- Stable URL of this page
https://metraipolis.com/documento/dc_6b091bb41bc5
How to cite
When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory — arXiv:2608.12888 — arXiv (en), https://arxiv.org/abs/2608.12888 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6b091bb41bc5 (Metraipolis archive dc_6b091bb41bc5, sha256 e72662abfb2156d5b8f0181cbe9511830c990f7121208f802679f0bf7cce383a)
BibTeX
@misc{dc6b091bb41bc5,
title = {When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory — arXiv:2608.12888},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12888},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6b091bb41bc5; sha256 e72662abfb2156d5b8f0181cbe9511830c990f7121208f802679f0bf7cce383a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12888. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agent-memory systems increasingly buy retrieval quality with structure, transforming raw conversation histories into summaries, embeddings, trees, or knowledge graphs before any question is asked. We ask how much of that benefit comes from the structure itself, rather than from competent retrieval over the raw history. We present ReFind, an agent-controlled search interface that builds no semantic structure at all: it leaves the conversation archive unmodified, indexes it lexically at turn granularity, and combines a generic iterative keyword-search loop with four chat-native controls grounded in empirical refinding work: session-aware rank fusion, local context expansion, temporal narrowing, and skipping already-inspected sessions. A separate reasoning stage answers from the collected evidence. Across a broad suite of conversational-memory tasks (single- and multi-hop QA, event ordering, and fact consolidation), roughly 2,800 questions on precise-retrieval and fact-tracking capabilities evaluated under the incremental multi-turn setting of MemoryAgentBench, ReFind attains the highest mean accuracy (58.2) of any system compared, above the strongest graph- and tree-based memory systems (HippoRAG 2, 53.2), all under a GPT-4o-mini backbone matched to every reused baseline. Controlled comparisons to single-shot BM25, a matched generic-agentic BM25 control, component removals, and agentic dense/hybrid variants separately support the roles of agent control, chat-native controls, and lexical retrieval. On LongMemEval-S/M, the same interface reaches 93.2 +/- 3.3 and 89.3 +/- 6.0 with GPT-5-mini. The results indicate that for precise, evidence-grounded questions over chat archives, much of the benefit credited to elaborate memory structures is recoverable by giving an agent controllable search over the unmodified record, with no LLM-based index construction at all. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.12888 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T04:17:42.382Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).