Metraipolis › archive › dc_406e5100bf99
M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization — arXiv:2609.34491
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34491
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:38:18.773Z
- SHA-256 of the archived text
058a1d836e02a5e581bac4c5f86fde396be2f20de5c6d119a87450a0838a2e6e- Stable URL of this page
https://metraipolis.com/documento/dc_406e5100bf99
How to cite
M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization — arXiv:2609.34491 — arXiv (en), https://arxiv.org/abs/2609.34491 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_406e5100bf99 (Metraipolis archive dc_406e5100bf99, sha256 058a1d836e02a5e581bac4c5f86fde396be2f20de5c6d119a87450a0838a2e6e)
BibTeX
@misc{dc406e5100bf99,
title = {M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization — arXiv:2609.34491},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34491},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_406e5100bf99; sha256 058a1d836e02a5e581bac4c5f86fde396be2f20de5c6d119a87450a0838a2e6e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34491. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Small-molecule optimization integrates medicinal-chemistry reasoning and computational evidence through iterative, multi-objective decisions. When large language models (LLMs) reason over optimization histories stored primarily in conversational context, they must recover candidate identities, prior evaluations, and task constraints to guide subsequent decisions. We present M3OS, a multi-agent LLM system that decouples molecular-design reasoning from optimization-state management through Monte Carlo graph search. A persistent graph links evaluated candidates, parent-child transformations and evaluation evidence, while rewards and visit statistics guide LLM-assisted parent selection. Two branches combine tool-driven candidate generation with knowledge- and case-guided medicinal-chemistry editing. An execution harness controls graph updates through structured output extraction, molecular validation and task-bound evaluation. Agents receive role-specific contexts, while the graph preserves optimization trajectories beyond their active contexts. Across three molecular optimization benchmarks, M3OS achieves higher success rates than baselines, supporting the integration of persistent search state, specialized agents and controlled execution for multi-constraint optimization. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Biomolecules (q-bio.BM). Pagina del lavoro: https://arxiv.org/abs/2609.34491 — 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 2026-10-07T22:14:28.206Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).