Skip to content

composable-models/llm_multiagent_debate

View on GitHub ↗Related repositories →

[Fork] Code for Improving Factuality and Reasoning in Language Models through Multiagent Debate

Python · active 2023-08-172026-05-20 (UTC)

Complete coverage26,515 / 26,515 hourly files (100%) · 2 absent upstream2023-08-152026-08-23 (UTC)
Events
407
Pushes
3
Pull requests
2
Issues
9
Stars
318
Forks
64

Activity over time

Daily event counts in the loaded window

Line chart, 1008 days from 2023-08-17 to 2026-05-20. Pushes: 3 total, peak 1 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 9 total, peak 1 in a day. Comments: 11 total, peak 3 in a day. Stars: 318 total, peak 4 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
yilundu8206
gauss59305002
fywang122020
20182118012001
sudo-Boris2001
FutureForMe2001
Beaudaniel2000
ShuangLI591100
floatingbigcat1000

Recent activity

Latest issues, pull requests and releases

  • Pull request#15fywang122025-09-24 05:57
  • Pull request#15fywang122025-09-24 05:56
  • Issue comment#14sudo-Boris2024-04-22 06:56
    Accuracy metric for gsm
  • Issue#14sudo-Boris2024-04-22 06:53
    Accuracy metric for gsm
  • Issue#10Beaudaniel2023-12-24 22:08
    Website Plans?
  • Issue#13floatingbigcat2023-12-12 06:12
    Prompt mismatch
  • Issue#11gauss59302023-11-17 11:37
    How to do summarization to reduce the context length?
  • Issue comment#12yilundu2023-10-09 11:03
    Can I call the open source LLM directly, why do you suggest to create an API?
  • Issue#1220182118012023-10-09 08:15
    Can I call the open source LLM directly, why do you suggest to create an API?
  • Issue comment#320182118012023-10-07 08:13
    How to use Open Source LLM for LLM Multi Agent Debate?
  • Issue comment#11yilundu2023-09-29 16:54
    How to do summarization to reduce the context length?
  • Issue comment#11gauss59302023-09-28 13:04
    How to do summarization to reduce the context length?
  • Issue#11gauss59302023-09-28 13:04
    How to do summarization to reduce the context length?
  • Issue comment#11gauss59302023-09-28 13:03
    How to do summarization to reduce the context length?
  • Issue comment#11yilundu2023-09-22 16:12
    How to do summarization to reduce the context length?
  • Issue#11gauss59302023-09-22 15:21
    How to do summarization to reduce the context length?
  • Issue#10Beaudaniel2023-09-08 23:40
    Website Plans?
  • Issue comment#9yilundu2023-09-05 13:24
    Repeat times of experiment results
  • Issue comment#9FutureForMe2023-09-04 14:16
    Repeat times of experiment results
  • Issue comment#9yilundu2023-09-04 14:06
    Repeat times of experiment results
  • Issue comment#9yilundu2023-09-04 13:55
    Repeat times of experiment results
  • Issue#9FutureForMe2023-09-04 03:52
    Repeat times of experiment results

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 318 stars here means stars gained during the window, not the repo's star count.