Metraipolis › archive › dc_6816bfd7fb6e

PharmAgent: Constraint-Aware Search with Frozen Language Models for Molecular Optimization — arXiv:2610.05431

Source
arXiv
Original
https://arxiv.org/abs/2610.05431
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:10.038Z
SHA-256 of the archived text
b630a02154747fec1392fdb38e33e5609bd17e0b62ec3d273f7057f4cb127d41
Stable URL of this page
https://metraipolis.com/documento/dc_6816bfd7fb6e

How to cite

PharmAgent: Constraint-Aware Search with Frozen Language Models for Molecular Optimization — arXiv:2610.05431 — arXiv, https://arxiv.org/abs/2610.05431 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6816bfd7fb6e (Metraipolis archive dc_6816bfd7fb6e, sha256 b630a02154747fec1392fdb38e33e5609bd17e0b62ec3d273f7057f4cb127d41)
BibTeX
@misc{dc6816bfd7fb6e,
  title = {PharmAgent: Constraint-Aware Search with Frozen Language Models for Molecular Optimization — arXiv:2610.05431},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05431},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6816bfd7fb6e; sha256 b630a02154747fec1392fdb38e33e5609bd17e0b62ec3d273f7057f4cb127d41},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05431. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Molecular optimization must improve target activity and satisfy developability constraints within limited evaluation budgets. Classical methods require tailored rules or training to incorporate chemical instructions and property feedback. Frozen language models can condition edits on this information, but need explicit constraint control and relevant experience. We therefore present PharmAgent, a constraint-aware molecular search method driven by adaptive external state. Its Lagrangian controller translates violations in accepted states into accumulated constraint pressure, keeping this history separate from current property measurements. Structure-indexed replay complements this feedback with relevant evaluated transitions that guide subsequent proposals. As a curriculum progressively activates constraints, candidates and the incumbent are compared under the same current objective, and the accepted state determines the next multiplier update. We derive an exact identity that characterizes how accepted-state violations accumulate in the controller's multipliers. Across five tasks with five independent runs, PharmAgent achieves a summed area under the target-score curves (AUC) of 3.9208 in target-only search, improving over MOLLEO by 37.3%. With online constraints, it achieves a property-adjusted AUC of 0.7076, improving over the strongest online baseline, ExLLM, by 53.8%. These results rank first among all evaluated methods in both target-only and constraint-aware search. The online comparison covers all five baseline frameworks. The full system leads every ablation variant in target quality, property-adjusted performance, and Pareto hypervolume. All five molecular cases reach feasible final states, documenting target gains and trade-offs.

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/2610.05431 — 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 2026-10-06T05:24:05.587Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).