composable-models / llm_multiagent_debate
ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate
β353Updated last year
Related projects β
Alternatives and complementary repositories for llm_multiagent_debate
- [NeurIPS 2022] πWebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentsβ276Updated 2 months ago
- Reasoning with Language Model is Planning with World Modelβ145Updated last year
- LLM Agora, debating between open-source LLMs to refine the answersβ52Updated last year
- Repo for paper "Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration"β315Updated 6 months ago
- Code for STaR: Bootstrapping Reasoning With Reasoning (NeurIPS 2022)β164Updated last year
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasksβ279Updated 3 weeks ago
- MAD: The first work to explore Multi-Agent Debate with Large Language Models :Dβ275Updated last year
- An Analytical Evaluation Board of Multi-turn LLM Agentsβ250Updated 6 months ago
- Code for Arxiv 2023: Improving Language Model Negociation with Self-Play and In-Context Learning from AI Feedbackβ201Updated last year
- LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.β625Updated last month
- ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings - NeurIPS 2023 (oral)β235Updated 7 months ago
- Source code for the paper "Active Prompting with Chain-of-Thought for Large Language Models"β219Updated 6 months ago
- Codes for our paper "ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate"β234Updated last month
- FireAct: Toward Language Agent Fine-tuningβ255Updated last year
- Chain-of-Hindsight, A Scalable RLHF Methodβ220Updated last year
- An extensible benchmark for evaluating large language models on planningβ291Updated 6 months ago
- [ACL 2024] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewβ102Updated 6 months ago
- Data and Code for Program of Thoughts (TMLR 2023)β243Updated 6 months ago
- VisualWebArena is a benchmark for multimodal agents.β244Updated last week
- Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)β164Updated this week
- Official implementation of paper "Cumulative Reasoning With Large Language Models" (https://arxiv.org/abs/2308.04371)β287Updated 2 months ago
- Official Implementation of Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimizationβ111Updated 6 months ago
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agenβ¦β255Updated last year
- β126Updated last year
- [NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinkingβ252Updated 4 months ago
- augmented LLM with self reflectionβ102Updated last year
- [ICLR 2024 Spotlight] FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Setsβ211Updated 10 months ago
- ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels β¦β240Updated last year
- [NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898β194Updated 6 months ago
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelβ465Updated last month