# CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review

arXiv: https://arxiv.org/abs/2609.05227 · HTML: https://mlsanity.com/paper/2609.05227/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 21 of 21)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024)
- [Construction of the Literature Graph in Semantic Scholar](https://mlsanity.com/paper/1805.02262/) (2018)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments](https://mlsanity.com/paper/2006.16437/) (2020)
- [Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis](https://mlsanity.com/paper/2407.12857/) (2024)
- [PeerReview4All: Fair and Accurate Reviewer Assignment in Peer Review](https://mlsanity.com/paper/1806.06237/) (2018)
- [Paper Matching with Local Fairness Constraints](https://mlsanity.com/paper/1905.11924/) (2019)
- [PaRe: A Paper-Reviewer Matching Approach Using a Common Topic Space](https://mlsanity.com/paper/1909.11258/) (2019)
- [Making Paper Reviewing Robust to Bid Manipulation Attacks](https://mlsanity.com/paper/2102.06020/) (2021)
- [Counterfactual Evaluation of Peer-Review Assignment Policies](https://mlsanity.com/paper/2305.17339/) (2023)
- [A SUPER* Algorithm to Optimize Paper Bidding in Peer Review](https://mlsanity.com/paper/2007.07079/) (2020)
- [A Dataset on Malicious Paper Bidding in Peer Review](https://mlsanity.com/paper/2207.02303/) (2022)
- [On the Detection of Reviewer-Author Collusion Rings From Paper Bidding](https://mlsanity.com/paper/2402.07860/) (2024)
- [Vulnerability of Text-Matching in ML/AI Conference Reviewer Assignments to Collusions](https://mlsanity.com/paper/2412.06606/) (2024)
- [Combating Collusion Rings is Hard but Possible](https://mlsanity.com/paper/2112.08444/) (2021)
- [A One-Size-Fits-All Approach to Improving Randomness in Paper Assignment](https://mlsanity.com/paper/2310.05995/) (2023)
- [Mitigating Skewed Bidding for Conference Paper Assignment](https://mlsanity.com/paper/2303.00435/) (2023)

## Built on by (most cited first, 1 of 1)

- [A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents](https://mlsanity.com/paper/2610.10468/) (2026)

## Abstract (arXiv)

Recent reports during the AAAI-27 review cycle highlight the risk of reviewers coordinating bids for reciprocal assignment advantage. Prior work treats bidding, reviewer assignment, and review manipulation as separate stages, leaving the lifecycle effects of collusive bidding unclear. Real-world analysis is further constrained by typically unobservable collusive intent and the lack of counterfactuals for the same conference. Motivated by this gap, we introduce alg, an end-to-end multi-agent simulacra framework for studying reviewer assignment integrity by holding the conference environment fixed and configuring LLM-driven reviewer agents with honest or collusive policies. We further develop an affinity-guided collusive bidding strategy that uses mutual reviewer-paper affinities to construct collusion rings and select target papers, producing expertise-consistent rather than arbitrarily targeted attacks. Controlled experiments show that collusive bidding more than doubles target-paper capture and that assigned colluders score target papers about two points higher than honest co-reviewers, while conference-wide effects remain comparatively modest. Evaluated bid-phase detectors provide only limited evidence of collusion: in a fixed-triplet detector stress test, native positive-bid graphs are confounded by benign affinity, while a Very-High-only diagnostic view enables precise but low-coverage local recovery.