Metraipolis › archive › dc_e2dda2367dc8

Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design — arXiv:2610.06190

Source
arXiv
Original
https://arxiv.org/abs/2610.06190
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:27.975Z
SHA-256 of the archived text
d317a0eb113e9e540905b4e47a835cd205e63327c5448dc431af8c4d8e123b2d
Stable URL of this page
https://metraipolis.com/documento/dc_e2dda2367dc8

How to cite

Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design — arXiv:2610.06190 — arXiv, https://arxiv.org/abs/2610.06190 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e2dda2367dc8 (Metraipolis archive dc_e2dda2367dc8, sha256 d317a0eb113e9e540905b4e47a835cd205e63327c5448dc431af8c4d8e123b2d)
BibTeX
@misc{dce2dda2367dc8,
  title = {Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design — arXiv:2610.06190},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06190},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e2dda2367dc8; sha256 d317a0eb113e9e540905b4e47a835cd205e63327c5448dc431af8c4d8e123b2d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06190. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) can reason over scientific literature to devise design strategies, yet fail to reliably implement them for biological sequences. While protein generative models learn sequence patterns, they lack the capacity to incorporate literature evidence for multi-step reflective reasoning, forming an evidence-to-execution gap between scientific reasoning and sequence manipulation. We present EASER (Evidence-Aware Sequence Engineering with Reflection), a reflective agent bridging reasoning and sequence generation via a learned property interface of offline-trained, fixed low-rank matrices. The agent steers a diffusion generator by combining these matrices, proposing intervention hypotheses (anchors, editable positions, control coefficients) grounded in retrieved evidence, sequence context and past results. A Probe-and-Steer mechanism validates interventions and allocates samples according to predicted property responses, with outcome reflection informing subsequent decisions. Evaluated on multi-objective antimicrobial peptide design (optimizing activity, non-hemolysis and non-toxicity), explicit hypothesis formulation delivers better multi-objective performance than direct action generation under identical decision conditions. Ablation studies verify the importance of evidence retrieval, episodic history, reflection and Probe-and-Steer. Over six repeated trials, EASER obtains the highest mean hypervolume and lowest mean IGD+ on screened candidates compared with competing baselines. Our work demonstrates how an executable property interface and iterative feedback link scientific reasoning to targeted peptide sequence generation.

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/2610.06190 — 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 2026-10-06T05:24:05.657Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).