Reason-to-Learn (R2L): Multi-Agent Knowledge Distillation for Lightweight LLMs in Sentiment Analysis

Le-Huy Tu, Quan Nguyen, Vincent NGUYEN, Johanna Bjorklund, Xuan-Son Vu


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.
Anthology ID:
2026.lrec-1.809
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
10301–10312
Language:
External URL:
https://lrec.elra.info/lrec2026-main-809
DOI:
10.63317/3aygmawej3my
Bibkey:
Cite (ACL):
Le-Huy Tu, Quan Nguyen, Vincent NGUYEN, Johanna Bjorklund, and Xuan-Son Vu. 2026. Reason-to-Learn (R2L): Multi-Agent Knowledge Distillation for Lightweight LLMs in Sentiment Analysis. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 10301–10312, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Reason-to-Learn (R2L): Multi-Agent Knowledge Distillation for Lightweight LLMs in Sentiment Analysis (Tu et al., LREC 2026)
Copy Citation: