<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-2026-reactr">
    <titleInfo>
        <title>ReActR: Reasoning through Error-Activated Reflection for LLM Post-Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lina</namePart>
        <namePart type="family">Sun</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>Although Large Language Models (LLMs) have demonstrated substantial proficiency in reasoning, current approaches focus disproportionately on scaling correct training samples, underexploring the value of incorrect reasoning trajectories. Motivated by how humans learn from mistakes, we propose ReActR (Reasoning through Error-Activated Reflection), a framework that enhances reasoning by learning reflective behaviors from erroneous trajectories. Specifically, ReActR comprises data construction and training. First, we synthesize multi-turn erroneous reasoning dataset spanning diverse error types and difficult levels via self-generation and targeted error generation. Second, we enhance the model’s capabilities through Supervised Fine-Tuning (SFT) on synthesized data and then apply Group Relative Policy Optimization (GRPO) with multiple reward signals to further refine reasoning performance. Extensive experiments across five benchmarks and three LLMs demonstrate that ReActR effectively enhances reasoning performance. Notably, on Llama-3-8B, ReActR achieves an average improvement of 3.5% across the five datasets.</abstract>
    <identifier type="citekey">sun-2026-reactr</identifier>
    <identifier type="doi">10.18653/v1/2026.acl-long.1993</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.1993/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>43017</start>
            <end>43028</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ReActR: Reasoning through Error-Activated Reflection for LLM Post-Training
%A Sun, Lina
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F sun-2026-reactr
%X Although Large Language Models (LLMs) have demonstrated substantial proficiency in reasoning, current approaches focus disproportionately on scaling correct training samples, underexploring the value of incorrect reasoning trajectories. Motivated by how humans learn from mistakes, we propose ReActR (Reasoning through Error-Activated Reflection), a framework that enhances reasoning by learning reflective behaviors from erroneous trajectories. Specifically, ReActR comprises data construction and training. First, we synthesize multi-turn erroneous reasoning dataset spanning diverse error types and difficult levels via self-generation and targeted error generation. Second, we enhance the model’s capabilities through Supervised Fine-Tuning (SFT) on synthesized data and then apply Group Relative Policy Optimization (GRPO) with multiple reward signals to further refine reasoning performance. Extensive experiments across five benchmarks and three LLMs demonstrate that ReActR effectively enhances reasoning performance. Notably, on Llama-3-8B, ReActR achieves an average improvement of 3.5% across the five datasets.
%R 10.18653/v1/2026.acl-long.1993
%U https://aclanthology.org/2026.acl-long.1993/
%U https://doi.org/10.18653/v1/2026.acl-long.1993
%P 43017-43028

Markdown (Informal)

[ReActR: Reasoning through Error-Activated Reflection for LLM Post-Training](https://aclanthology.org/2026.acl-long.1993/) (Sun, ACL 2026)

• ReActR: Reasoning through Error-Activated Reflection for LLM Post-Training (Sun, ACL 2026)

ACL

• Lina Sun. 2026. ReActR: Reasoning through Error-Activated Reflection for LLM Post-Training. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 43017–43028, San Diego, California, United States. Association for Computational Linguistics.