@inproceedings{gao-etal-2026-feedback,
title = "Feedback to Reasoning: {LLM}-Assisted Molecular Optimization with Domain Feedback and Historical Reasoning",
author = "Gao, Wenhan and
Fan, Xiran and
Yeh, Chin-Chia Michael and
Sun, Jiarui and
Chen, Yuzhong and
Pan, Menghai and
Das, Mahashweta and
Liu, Yi",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.619/",
pages = "12735--12754",
ISBN = "979-8-89176-395-1",
abstract = "The success of large language models (LLMs) across domains highlights their potential in scientific tasks, with molecular optimization being a promising frontier. Traditionally, this optimization relies on iterative expert feedback to refine molecules toward desired properties, a process well aligned with LLMs' strengths. **As an experience-driven task, molecular optimization depends critically on the domain feedback and accumulation of historical knowledge. However, none of the existing methods fully leverages such feedback and historical knowledge with reasoning traces and chemical insights.** In this work, we propose F2R: Feedback to Reasoning, a conversational molecular optimization pipeline that enables LLMs to accumulate and retrieve past actions, rationales, and feedback. Like humans, LLMs can generate imperfect reasoning; F2R is the first framework to use detailed domain feedback to critique and improve this reasoning. This transforms LLMs from passive text generators into agentic experts that learn both actions and reasoning from experience. Consequently, F2R shows remarkable performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2026-feedback">
<titleInfo>
<title>Feedback to Reasoning: LLM-Assisted Molecular Optimization with Domain Feedback and Historical Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenhan</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiran</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chin-Chia</namePart>
<namePart type="given">Michael</namePart>
<namePart type="family">Yeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarui</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuzhong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menghai</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahashweta</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>The success of large language models (LLMs) across domains highlights their potential in scientific tasks, with molecular optimization being a promising frontier. Traditionally, this optimization relies on iterative expert feedback to refine molecules toward desired properties, a process well aligned with LLMs’ strengths. **As an experience-driven task, molecular optimization depends critically on the domain feedback and accumulation of historical knowledge. However, none of the existing methods fully leverages such feedback and historical knowledge with reasoning traces and chemical insights.** In this work, we propose F2R: Feedback to Reasoning, a conversational molecular optimization pipeline that enables LLMs to accumulate and retrieve past actions, rationales, and feedback. Like humans, LLMs can generate imperfect reasoning; F2R is the first framework to use detailed domain feedback to critique and improve this reasoning. This transforms LLMs from passive text generators into agentic experts that learn both actions and reasoning from experience. Consequently, F2R shows remarkable performance.</abstract>
<identifier type="citekey">gao-etal-2026-feedback</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.619/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>12735</start>
<end>12754</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Feedback to Reasoning: LLM-Assisted Molecular Optimization with Domain Feedback and Historical Reasoning
%A Gao, Wenhan
%A Fan, Xiran
%A Yeh, Chin-Chia Michael
%A Sun, Jiarui
%A Chen, Yuzhong
%A Pan, Menghai
%A Das, Mahashweta
%A Liu, Yi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F gao-etal-2026-feedback
%X The success of large language models (LLMs) across domains highlights their potential in scientific tasks, with molecular optimization being a promising frontier. Traditionally, this optimization relies on iterative expert feedback to refine molecules toward desired properties, a process well aligned with LLMs’ strengths. **As an experience-driven task, molecular optimization depends critically on the domain feedback and accumulation of historical knowledge. However, none of the existing methods fully leverages such feedback and historical knowledge with reasoning traces and chemical insights.** In this work, we propose F2R: Feedback to Reasoning, a conversational molecular optimization pipeline that enables LLMs to accumulate and retrieve past actions, rationales, and feedback. Like humans, LLMs can generate imperfect reasoning; F2R is the first framework to use detailed domain feedback to critique and improve this reasoning. This transforms LLMs from passive text generators into agentic experts that learn both actions and reasoning from experience. Consequently, F2R shows remarkable performance.
%U https://aclanthology.org/2026.findings-acl.619/
%P 12735-12754
Markdown (Informal)
[Feedback to Reasoning: LLM-Assisted Molecular Optimization with Domain Feedback and Historical Reasoning](https://aclanthology.org/2026.findings-acl.619/) (Gao et al., Findings 2026)
ACL
- Wenhan Gao, Xiran Fan, Chin-Chia Michael Yeh, Jiarui Sun, Yuzhong Chen, Menghai Pan, Mahashweta Das, and Yi Liu. 2026. Feedback to Reasoning: LLM-Assisted Molecular Optimization with Domain Feedback and Historical Reasoning. In Findings of the Association for Computational Linguistics: ACL 2026, pages 12735–12754, San Diego, California, United States. Association for Computational Linguistics.