# A Cooperative Multi-Agent Framework for Zero-Shot Named Entity Recognition

arXiv: https://arxiv.org/abs/2502.18702 · HTML: https://mlsanity.com/paper/2502.18702/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 57 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 31)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://mlsanity.com/paper/2310.18940/) (2023)
- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets](https://mlsanity.com/paper/2305.18486/) (2023)
- [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023)
- [Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation](https://mlsanity.com/paper/2310.01320/) (2023)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [Semi-supervised sequence tagging with bidirectional language models](https://mlsanity.com/paper/1705.00108/) (2017)
- [Portuguese Named Entity Recognition using BERT-CRF](https://mlsanity.com/paper/1909.10649/) (2019)
- [Empirical Study of Zero-Shot NER with ChatGPT](https://mlsanity.com/paper/2310.10035/) (2023)
- [Learning or Self-aligning? Rethinking Instruction Fine-tuning](https://mlsanity.com/paper/2402.18243/) (2024)
- [The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders](https://mlsanity.com/paper/2109.06939/) (2021)
- [Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation](https://mlsanity.com/paper/2305.14386/) (2023)
- [LIQUID: A Framework for List Question Answering Dataset Generation](https://mlsanity.com/paper/2302.01691/) (2023)
- [Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models](https://mlsanity.com/paper/2311.08921/) (2023)
- [LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty](https://mlsanity.com/paper/2402.10573/) (2024)
- [Prompting-based Synthetic Data Generation for Few-Shot Question Answering](https://mlsanity.com/paper/2405.09335/) (2024)
- [A Linguistic Study on Relevance Modeling in Information Retrieval](https://mlsanity.com/paper/2103.00956/) (2021)

## Built on by (most cited first, 6 of 6)

- [DeepShop: A Benchmark for Deep Research Shopping Agents](https://mlsanity.com/paper/2506.02839/) (2025)
- [Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models](https://mlsanity.com/paper/2509.24365/) (2025)
- [PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature](https://mlsanity.com/paper/2510.10909/) (2025)
- [DeepMEL: A Multi-Agent Collaboration Framework for Multimodal Entity Linking](https://mlsanity.com/paper/2508.15876/) (2025)
- [A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition](https://mlsanity.com/paper/2610.02970/) (2026)
- [SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition](https://mlsanity.com/paper/2605.03706/) (2026)

## Abstract (arXiv)

Zero-shot named entity recognition (NER) aims to develop entity recognition systems from unannotated text corpora. This task presents substantial challenges due to minimal human intervention. Recent work has adapted large language models (LLMs) for zero-shot NER by crafting specialized prompt templates. It advances model self-learning abilities by incorporating self-annotated demonstrations. However, two important challenges persist: (i) Correlations between contexts surrounding entities are overlooked, leading to wrong type predictions or entity omissions. (ii) The indiscriminate use of task demonstrations, retrieved through shallow similarity-based strategies, severely misleads LLMs during inference. In this paper, we introduce the cooperative multi-agent system (CMAS), a novel framework for zero-shot NER that uses the collective intelligence of multiple agents to address the challenges outlined above. CMAS has four main agents: (i) a self-annotator, (ii) a type-related feature (TRF) extractor, (iii) a demonstration discriminator, and (iv) an overall predictor. To explicitly capture correlations between contexts surrounding entities, CMAS reformulates NER into two subtasks: recognizing named entities and identifying entity type-related features within the target sentence. To enable controllable utilization of demonstrations, a demonstration discriminator is established to incorporate the self-reflection mechanism, automatically evaluating helpfulness scores for the target sentence. Experimental results show that CMAS significantly improves zero-shot NER performance across six benchmarks, including both domain-specific and general-domain scenarios. Furthermore, CMAS demonstrates its effectiveness in few-shot settings and with various LLM backbones.