Even without human cognitive limits, agents:

- Heavily over-weight ratings
- Over-weight cheaper items when ratings are matched
- Are swayed by trivial order effects
- Fall for simple nudges (e.g. “Best seller”)

These are systematic, often large effects.

🧵5/9

The main finding: LLM agents are not the rational, utility-maximizing actors we might hope for.

Rather, they are strongly biased by these cues. We found agents are often 3-10x+ more susceptible to nudges and superficial attribute differences than our human baseline.

🧵4/9

🚨New Preprint 🚨

Current agent evals mostly measure competence, but miss behavior e.g. are their decisions stable, rational, manipulable, human-like?

We introduce ABxLAB, a framework for studying agent behavior. Using it we create an agentic consumer behavior benchmark.

🧵1/9

✨Contrastive Learning from Synthetic Audio Doppelgängers #ICLR2025✨ w/
@nikhilsinghmus.bsky.social

Our method learns useful audio representations with randomly synthesized sounds (often better than real data!)

🌐Project: doppelgangers.media.mit.edu
📄Paper: arxiv.org/abs/2406.05923

🧵1/3

Excited to present our new paper on nudging LLMs (👉🤖) as a spotlight talk at the NeurIPS Behavioral ML Workshop! @neuripsconf.bsky.social

w/ Nikhil Singh* (@nikhilsinghmus.bsky.social) and Pattie Maes

🔗 openreview.net/forum?id=chb...

🧵 1/3