MoreAgentsIsAllYouNeed / AgentForestLinks
We present the first systematic study on the scaling property of raw agents instantiated by LLMs. We find that performance scales with the increase in the number of agents, using the simple(st) way of sampling and voting. Our method is called Agent Forest, as a tribute to the classic Random Forest.
☆124Updated 8 months ago
Alternatives and similar repositories for AgentForest
Users that are interested in AgentForest are comparing it to the libraries listed below
Sorting:
- Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"☆149Updated 2 weeks ago
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆93Updated 2 weeks ago
- An Analytical Evaluation Board of Multi-turn LLM Agents [NeurIPS 2024 Oral]☆326Updated last year
- Official implementation of paper "On the Diagram of Thought" (https://arxiv.org/abs/2409.10038)☆185Updated 2 months ago
- This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'☆118Updated 3 weeks ago
- An implemtation of Everyting of Thoughts (XoT).☆143Updated last year
- ☆121Updated last year
- Official implementation for "ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization"☆78Updated last month
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆219Updated last month
- [NAACL 2025] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents☆228Updated 4 months ago
- ☆114Updated 5 months ago
- Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"☆110Updated 8 months ago
- [ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning☆228Updated 5 months ago
- ☆318Updated 9 months ago
- AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reaso…☆116Updated 3 months ago
- Meta-CoT: Generalizable Chain-of-Thought Prompting in Mixed-task Scenarios with Large Language Models☆97Updated last year
- ☆182Updated 5 months ago
- Framework and toolkits for building and evaluating collaborative agents that can work together with humans.☆86Updated 2 months ago
- ☆142Updated last year
- [ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"☆145Updated 3 months ago
- [NeurIPS 2024] Agent Planning with World Knowledge Model☆141Updated 6 months ago
- [NeurIPS 2024] Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?☆125Updated 10 months ago
- ☆47Updated 2 weeks ago
- The All-in-one Judge Models introduced by Opencompass☆93Updated 4 months ago
- [ACL 2025] Agentic Knowledgeable Self-awareness☆72Updated last week
- xLAM: A Family of Large Action Models to Empower AI Agent Systems☆465Updated last week
- [ICLR 2025] Benchmarking Agentic Workflow Generation☆100Updated 4 months ago
- A banchmark list for evaluation of large language models.☆128Updated last month
- ☆232Updated 10 months ago
- Code for the paper: "Learning to Reason without External Rewards"☆306Updated last week