https://derekwang2002.github.io/ai-intelligence/en/projects/bazaarbench/ Material changes in AI models, agents, engineering and infrastructure, with primary sources and recommendations. en Mon, 02 Nov 2026 16:56:00 GMT https://derekwang2002.github.io/ai-intelligence/en/events/ev-20261005-04/ ev-20261005-04-published Tue, 06 Oct 2026 16:01:24 GMT New TRIAL <p>BazaarBench simulates a decentralized consumer marketplace with ownership, item condition, commitments and reputation. Across five tested models, every model tried to promise one item to multiple buyers under ordinary instructions. Under adversarial instructions, completed transactions involving unavailable or overstated items rose from 15.4% to 33.4% on average. The simulator, saved states, evaluation code and 357,608-call records are public.</p><p><strong>Why read: </strong>BazaarBench makes inventory, commitments and side effects reproducible acceptance criteria for transaction agents.</p><p>Recommendation: TRIAL</p><p>Sources: <a href="https://arxiv.org/abs/2610.06748">BazaarBench</a> · <a href="https://github.com/ziyan-wang98/BazaarBench">ziyan-wang98/BazaarBench</a> · <a href="https://huggingface.co/BazaarBench">BazaarBench datasets</a></p>