This repository accompanies research on improving language model factuality and reasoning through multi-agent debate.

github.com/composable-models/llm_multiagent_de…
Multiagent Debate homepage screenshot

About Multiagent Debate

Multiagent Debate is a research repository containing Python scripts for running multiagent debate experiments from the paper Improving Factuality and Reasoning in Language Models through Multiagent Debate. The code is grouped into math, GSM, biography and MMLU folders, with commands for generating answers and evaluating results for several tasks.

Pricing is not clearly stated.

Key features

  • Task folders for arithmetic, GSM, biography and MMLU
  • Generation commands gen_math.py, gen_gsm.py, gen_conversation.py and gen_mmlu.py
  • Evaluation commands eval_gsm.py, eval_conversation.py and eval_mmlu.py
  • Download links for the GSM and MMLU datasets
  • BibTeX citation for the associated paper
Best for: Running multiagent debate experiments on arithmetic, grade school math, biography and MMLU tasks.
Watch out for
  • The README describes the implementation as preliminary.

Multiagent Debate at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Details verified
Oct 22, 2026 · Official source
Open source
Not stated
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

Multiagent Debate alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in Models & ML Research

Well-known listings from the same topic.

All 69
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing