TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration
Weiya Li, Junjie Chen, Bei Li, Boyang Liu, Zichen Wen, Nuanqiao Shan, Xiaoqian Liu, Anping Liu, Huajie Liu, Hu Song, Linfeng Zhang

TL;DR
TACTIC introduces a cognitively inspired multi-agent framework for machine translation, leveraging human-like cognitive strategies to enhance translation quality with state-of-the-art results across multiple benchmarks.
Contribution
The paper presents a novel multi-agent framework, TACTIC, that incorporates cognitive translation insights into LLM-based translation, improving performance over existing models.
Findings
Achieves state-of-the-art translation quality on FLORES-200 and WMT24 benchmarks.
Outperforms GPT-4.1 and DeepSeek models in translation tasks.
Demonstrates the effectiveness of cognitive-inspired multi-agent collaboration.
Abstract
Machine translation has long been a central task in natural language processing. With the rapid advancement of large language models (LLMs), there has been remarkable progress in translation quality. However, fully realizing the translation potential of LLMs remains an open challenge. Recent studies have explored multi-agent systems to decompose complex translation tasks into collaborative subtasks, showing initial promise in enhancing translation quality through agent cooperation and specialization. Nevertheless, existing multi-agent translation frameworks largely neglect foundational insights from cognitive translation studies. These insights emphasize how human translators employ different cognitive strategies, such as balancing literal and free translation, refining expressions based on context, and iteratively evaluating outputs. To address this limitation, we propose a cognitively…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Multimodal Machine Learning Applications
MethodsLinear Layer · Adam · Byte Pair Encoding · Attention Is All You Need · Multi-Head Attention · Dropout · Label Smoothing · Dense Connections · Residual Connection · Position-Wise Feed-Forward Layer
