# BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents

arXiv: https://arxiv.org/abs/2610.06748 · HTML: https://mlsanity.com/paper/2610.06748/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 61 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

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

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast](https://mlsanity.com/paper/2402.08567/) (2024)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems](https://mlsanity.com/paper/2410.07283/) (2024)
- [Evil Geniuses: Delving into the Safety of LLM-based Agents](https://mlsanity.com/paper/2311.11855/) (2023)
- [Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents](https://mlsanity.com/paper/2502.15840/) (2025)
- [Finance Agent Benchmark: Benchmarking LLMs on Real-world Financial Research Tasks](https://mlsanity.com/paper/2508.00828/) (2025)
- [INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent](https://mlsanity.com/paper/2412.18174/) (2024)
- [Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets](https://mlsanity.com/paper/2510.25779/) (2025)
- [The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets](https://mlsanity.com/paper/2506.00073/) (2025)
- [FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use](https://mlsanity.com/paper/2603.08262/) (2026)
- [FinGAIA: A Chinese Benchmark for AI Agents in Real-World Financial Domain](https://mlsanity.com/paper/2507.17186/) (2025)
- [Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals](https://mlsanity.com/paper/2603.03258/) (2026)
- [FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol](https://mlsanity.com/paper/2603.24943/) (2026)
- [FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluation](https://mlsanity.com/paper/2602.03130/) (2026)
- [Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation](https://mlsanity.com/paper/2602.16990/) (2026)
- [Technical Report: Evaluating Goal Drift in Language Model Agents](https://mlsanity.com/paper/2505.02709/) (2025)
- [E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation](https://mlsanity.com/paper/2608.30730/) (2026)

## Abstract (arXiv)

In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation. Large language model (LLM) agents now act for users, raising risks to their money, privacy, and reputation. We introduce BazaarBench, a simulated C2C marketplace and benchmark for evaluating the safety of these agents. It tracks ownership, item condition, and commitments across transactions, combining record checks with rubric-based LLM judgments to identify six failure types across five stages. We run three base markets for 30 simulated days, each with 100 agents using one model and inventories drawn from a public eBay sample. Across 45 continuations, we evaluate five models under ordinary instructions, deadline pressure, or adversarial instructions to exploit other traders. Each continuation runs for seven simulated days from a copy of a market's day-30 state. The tested model controls the same 20 selected agents, retaining their personas, inventories, and histories, while the other 80 keep the base model. All five models attempt to promise the same item to multiple buyers under ordinary instructions. Adding targets and deadlines increases these attempts for every model. Under adversarial instructions, the share of tested sellers' committed transactions completed despite unavailable items or overstated conditions rises from 15.4% to 33.4%, reaching 55.5% for GPT-5.4. Averaged across models and markets, simulated weekly earnings per tested agent rise from USD 20 under ordinary instructions to USD 33 under adversarial instructions. Most of the increase comes from items the sellers never held. We release the simulator, saved market states, evaluation code, and records covering 357,608 agent model calls for evaluating new models and developing safer marketplace agents.