@inproceedings{tu-etal-2026-reason,
title = "Reason-to-Learn ({R}2{L}): Multi-Agent Knowledge Distillation for Lightweight {LLM}s in Sentiment Analysis",
author = "Tu, Le-Huy and
Nguyen, Quan and
NGUYEN, Vincent and
Bjorklund, Johanna and
Vu, Xuan-Son",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.809/",
doi = "10.63317/3aygmawej3my",
pages = "10301--10312",
abstract = "Large Language Models (LLMs) boast remarkable capabilities but face deployment challenges due to computational demands. We introduce Reason-to-Learn (R2L), a novel multi-agent collaborative knowledge distillation framework enabling small LLMs to learn from a distributed system of specialized agent models. Our architecture employs multiple autonomous teacher agents, each with distinct expertise and reasoning capabilities, coordinated by a meta-agent that orchestrates knowledge synthesis and conflict resolution. Unlike prior methods, our flexible four-phase process (Detection, Processing, Rationale Generation, Aggregation) leverages agent-based communication protocols and consensus mechanisms for cross-architecture knowledge transfer, demonstrated primarily on Vietnamese sentiment analysis. Experimental results are definitive: our lightweight R2L-Students (1-1.5B) consistently outperform the individual specialized agents (Qwen32B, Llama70B) and the GPT-4o meta-agent coordinator, especially on complex ABSA tasks. Ablation studies confirm our multi-agent collaborative approach outperformed traditional fine-tuning and single-agent distillation. Furthermore, R2L enhance generalizability of lightweight LLMs: our Vietnamese-trained student achieves strong zero-shot cross-lingual performance on Swedish ABSA (Svensk ABSAbank-Imm), with Krippendorff{'}s Alpha scores competitive with the specialized agents. R2L offers an efficient path to compact, high-performing specialist models through coordinated multi-agent learning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tu-etal-2026-reason">
<titleInfo>
<title>Reason-to-Learn (R2L): Multi-Agent Knowledge Distillation for Lightweight LLMs in Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Le-Huy</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">NGUYEN</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Bjorklund</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan-Son</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) boast remarkable capabilities but face deployment challenges due to computational demands. We introduce Reason-to-Learn (R2L), a novel multi-agent collaborative knowledge distillation framework enabling small LLMs to learn from a distributed system of specialized agent models. Our architecture employs multiple autonomous teacher agents, each with distinct expertise and reasoning capabilities, coordinated by a meta-agent that orchestrates knowledge synthesis and conflict resolution. Unlike prior methods, our flexible four-phase process (Detection, Processing, Rationale Generation, Aggregation) leverages agent-based communication protocols and consensus mechanisms for cross-architecture knowledge transfer, demonstrated primarily on Vietnamese sentiment analysis. Experimental results are definitive: our lightweight R2L-Students (1-1.5B) consistently outperform the individual specialized agents (Qwen32B, Llama70B) and the GPT-4o meta-agent coordinator, especially on complex ABSA tasks. Ablation studies confirm our multi-agent collaborative approach outperformed traditional fine-tuning and single-agent distillation. Furthermore, R2L enhance generalizability of lightweight LLMs: our Vietnamese-trained student achieves strong zero-shot cross-lingual performance on Swedish ABSA (Svensk ABSAbank-Imm), with Krippendorff’s Alpha scores competitive with the specialized agents. R2L offers an efficient path to compact, high-performing specialist models through coordinated multi-agent learning.</abstract>
<identifier type="citekey">tu-etal-2026-reason</identifier>
<identifier type="doi">10.63317/3aygmawej3my</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.809/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10301</start>
<end>10312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reason-to-Learn (R2L): Multi-Agent Knowledge Distillation for Lightweight LLMs in Sentiment Analysis
%A Tu, Le-Huy
%A Nguyen, Quan
%A NGUYEN, Vincent
%A Bjorklund, Johanna
%A Vu, Xuan-Son
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F tu-etal-2026-reason
%X Large Language Models (LLMs) boast remarkable capabilities but face deployment challenges due to computational demands. We introduce Reason-to-Learn (R2L), a novel multi-agent collaborative knowledge distillation framework enabling small LLMs to learn from a distributed system of specialized agent models. Our architecture employs multiple autonomous teacher agents, each with distinct expertise and reasoning capabilities, coordinated by a meta-agent that orchestrates knowledge synthesis and conflict resolution. Unlike prior methods, our flexible four-phase process (Detection, Processing, Rationale Generation, Aggregation) leverages agent-based communication protocols and consensus mechanisms for cross-architecture knowledge transfer, demonstrated primarily on Vietnamese sentiment analysis. Experimental results are definitive: our lightweight R2L-Students (1-1.5B) consistently outperform the individual specialized agents (Qwen32B, Llama70B) and the GPT-4o meta-agent coordinator, especially on complex ABSA tasks. Ablation studies confirm our multi-agent collaborative approach outperformed traditional fine-tuning and single-agent distillation. Furthermore, R2L enhance generalizability of lightweight LLMs: our Vietnamese-trained student achieves strong zero-shot cross-lingual performance on Swedish ABSA (Svensk ABSAbank-Imm), with Krippendorff’s Alpha scores competitive with the specialized agents. R2L offers an efficient path to compact, high-performing specialist models through coordinated multi-agent learning.
%R 10.63317/3aygmawej3my
%U https://aclanthology.org/2026.lrec-1.809/
%U https://doi.org/10.63317/3aygmawej3my
%P 10301-10312
Markdown (Informal)
[Reason-to-Learn (R2L): Multi-Agent Knowledge Distillation for Lightweight LLMs in Sentiment Analysis](https://aclanthology.org/2026.lrec-1.809/) (Tu et al., LREC 2026)
ACL