Skip to content

kmchandy/DisSysLab-Debate

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DisSysLab-Debate

Research experiments on heterogeneous LLM-agent panels using DisSysLab as the experimental platform.

Status

Pre-pilot. Phase 1 (single-agent calibration) starts July 2026.

Research questions

  1. When does a panel of heterogeneous agents (different temperatures, possibly different models) with one or more moderators outperform a single agent on a given problem class?
  2. How does inter-agent error correlation modulate the benefit of panel deliberation?
  3. What moderator strategies — concatenation, critique-and-revise, rationale-exchange — help most, and under what conditions?

Experimental plan

Phase What Status
1 Calibrate p(T) for 4-5 (model, temperature) configurations on a fixed problem class (~200 problems each). not started
2 Measure inter-agent error correlation for the configurations from Phase 1. not started
3 Pilot panel study: 3 panel configurations × 2 moderator strategies × 100 problems. not started
4 Working notes / draft paper with preliminary findings. not started

Built on

DisSysLab — a framework for building offices of agents in plain English. This repo depends on dissyslab as a regular PyPI package.

Related work

  • Du et al. (2023) "Improving Factuality and Reasoning in Language Models through Multiagent Debate."
  • Liang et al. (2024) "Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate."
  • Condorcet (1785) — foundational voting theorem for jury aggregation.
  • Ladha (1993) — extensions of Condorcet to correlated voters.

License

MIT

About

Models of moderated panels of agents solving problems using DisSysLab

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors