# PD3: A Project Duplication Detection Framework via Adapted Multi-Agent Debate

arXiv: https://arxiv.org/abs/2505.17492 · HTML: https://mlsanity.com/paper/2505.17492/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 55 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 20 of 20)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization](https://mlsanity.com/paper/1906.03741/) (2019)
- [jina-embeddings-v3: Multilingual Embeddings With Task LoRA](https://mlsanity.com/paper/2409.10173/) (2024)
- [Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate](https://mlsanity.com/paper/2305.11595/) (2023)
- [Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication](https://mlsanity.com/paper/2312.01823/) (2023)
- [GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion](https://mlsanity.com/paper/2409.14051/) (2024)
- [Let Models Speak Ciphers: Multiagent Debate through Embeddings](https://mlsanity.com/paper/2310.06272/) (2023)
- [TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy](https://mlsanity.com/paper/2406.11678/) (2024)
- [MReD: A Meta-Review Dataset for Structure-Controllable Text Generation](https://mlsanity.com/paper/2110.07474/) (2021)
- [OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Services](https://mlsanity.com/paper/2103.02410/) (2021)
- [WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval](https://mlsanity.com/paper/1805.03797/) (2018)
- [DEBATE: Devil's Advocate-Based Assessment and Text Evaluation](https://mlsanity.com/paper/2405.09935/) (2024)
- [Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction](https://mlsanity.com/paper/2406.12197/) (2024)
- [Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction](https://mlsanity.com/paper/2504.05358/) (2025)

## Built on by (most cited first, 2 of 2)

- [Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges](https://mlsanity.com/paper/2607.26212/) (2026)
- [Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate](https://mlsanity.com/paper/2610.18240/) (2026)

## Abstract (arXiv)

Project duplication detection is critical for project quality assessment because it helps avoid investment in repeated proposals. Existing methods usually cast it as ranking and rely on surface matching or direct large language models judging, often missing practical needs in set-level reference selection. We recast the task as many-to-many reference set selection, which requires broad candidate information and fair decomposed comparison under context limits. We propose PD3, a framework for Project Duplication Detection via adapted multi-agent Debate. PD3 combines local multi-agent debate with global round-robin scheduling to retrieve the relevant project set. Theoretically, this scheduler guarantees fair comparison through balanced exposure and comparison context. PD3 also produces quantitative duplication scores and qualitative overlap feedback. On 800+ real-world power projects, PD3 outperforms the strongest baselines by 4.05% in relevant reference selection and 9.77% in duplication score generation. We deploy Review Dingdang, an online platform, which has helped save 13.44 million across 442 new projects.