Akbar et al.
A belief layer lets LLM agents' stubbornness be set and verified
Bayesian Chronicle Agents separate belief from speech, enabling controllable opinion regimes with verifiable parameters.
Top University
Hafsa Akbar · Daniel Platnick · Marjan Alirezaie · Hossein Rahnama
MIT Media Lab · Flybits Labs · Creative AI Hub · Toronto Metropolitan University
Research Digest··2 min read
Thread:Multi-Agent Coordination
The authors introduce Bayesian Chronicle Agents (BCA), a minimal belief layer that explicitly models each LLM agent's stance as a probability updated by Bayesian inference upon hearing utterances.
Why this paper
From MIT Media Lab and 3 others · Released code · Part of Multi-Agent Coordination, now 24 papers
In one line
A Bayesian belief layer with a stubbornness parameter enables controllable and auditable opinion dynamics in LLM agents.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§