4 papers
TrustBound: Mechanized Completeness for Payment Epochs Initiated by AI Agents
Sandip Nandi, Aishwarya Bose, Apurba Bose +1
Payment operations requested by an AI agent may remain executable, or their outcomes unresolved, after the agent has stopped. We study when a trusted payment service can account fo…
TradeGauntlet: Evaluating Compliance Controls for Autonomous Trading Agents
Sandip Nandi, Aishwarya Bose, Apurba Bose +1
Autonomous trading agents need controls that prevent problematic orders without making legitimate tasks impractical. We study this aspect of agentic compliance with TradeGauntlet,…
Goodhart in the Planner: Sampling-Based Control Exploits Rewards Learned from Human Preferences
Soovadeep Bakshi, Apurba Bose
Robots increasingly plan by searching against a reward model learned from human preferences. We measure what this search does to the true objective. On HalfCheetah and Hopper with…
Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena
Soovadeep Bakshi, Apurba Bose, Aishwarya Bose +1
Chatbot Arena gives each language model one Bradley-Terry score, which fixes how often any model should beat any other. Choice theory predicts where this fails: near-copies are com…