Metraipolis › archive › dc_d024a26fadd8
Locating and Closing Information Gaps in Multi-Agent Systems — arXiv:2610.40186
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40186
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:10:44.348Z
- SHA-256 of the archived text
0a850a4db09ec277465f314cb47a8d795f20c63b567377fd6bb02306336cd216- Stable URL of this page
https://metraipolis.com/documento/dc_d024a26fadd8
How to cite
Locating and Closing Information Gaps in Multi-Agent Systems — arXiv:2610.40186 — arXiv (en), https://arxiv.org/abs/2610.40186 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d024a26fadd8 (Metraipolis archive dc_d024a26fadd8, sha256 0a850a4db09ec277465f314cb47a8d795f20c63b567377fd6bb02306336cd216)
BibTeX
@misc{dcd024a26fadd8,
title = {Locating and Closing Information Gaps in Multi-Agent Systems — arXiv:2610.40186},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40186},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d024a26fadd8; sha256 0a850a4db09ec277465f314cb47a8d795f20c63b567377fd6bb02306336cd216},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40186. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-step Web tasks often require several LLM agents to gather and combine evidence. The communication graph of a fixed workflow restricts which agents can read each other's outputs: evidence retrieved by one agent may never reach the agent that needs it, leaving an information gap and an incomplete or incorrect answer. Adding a connection can deliver the missing evidence, but can also lead the receiver to adopt an incorrect upstream conclusion that displaces a correct answer; the final output alone does not separate the two. We propose Selective Probing and Link Insertion for Closing information gaps in multi-agent Execution (SPLICE), which locates information gaps per query and decides what to adopt after adding an edge. After the original workflow runs, SPLICE uses the query and node outputs to locate a possible gap, adds one directed edge from a source to a receiver to deliver the relevant evidence, and re-executes the receiver and affected downstream nodes, producing a candidate answer. The adoption decision reads both the final answers of the two runs and the process changes the edit caused inside the workflow: how far the receiver moved, where its new content came from, and whether the change reached the final answer. A selector trained on these process features chooses between adopting the candidate answer and retaining the original. On five benchmarks, SPLICE raises the task score on Web tool use by 8.0% and the mean score on four reasoning and planning benchmarks by 5.7% relative to the static skeleton, at 1.25 to 1.44$\times$ the skeleton's cost, and transfers zero-shot to four unseen backbones. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.40186 — 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 2026-10-31T06:07:08.553Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).