aymeric-roucher / GAIA
Beating the GAIA benchmark with Transformers Agents. π
β103Updated last month
Alternatives and similar repositories for GAIA:
Users that are interested in GAIA are comparing it to the libraries listed below
- β117Updated 7 months ago
- Code repo for "Agent Instructs Large Language Models to be General Zero-Shot Reasoners"β104Updated 6 months ago
- π§ Compare how Agent systems perform on several benchmarks. ππβ89Updated 5 months ago
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and β¦β336Updated 9 months ago
- AWM: Agent Workflow Memoryβ252Updated last month
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language Mβ¦β207Updated 4 months ago
- Repository for βPlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makersβ, NAACL24β137Updated 9 months ago
- β156Updated 6 months ago
- Official repo for "LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs".β227Updated 6 months ago
- Banishing LLM Hallucinations Requires Rethinking Generalizationβ272Updated 8 months ago
- β89Updated 6 months ago
- Official repo for "Make Your LLM Fully Utilize the Context"β254Updated 10 months ago
- β120Updated 9 months ago
- Official implementation of paper "On the Diagram of Thought" (https://arxiv.org/abs/2409.10038)β177Updated last week
- Client Code Examples, Use Cases and Benchmarks for Enterprise h2oGPTe RAG-Based GenAI Platformβ83Updated last week
- β160Updated 7 months ago
- β51Updated 7 months ago
- This repository implements the chain of verification paper by Meta AIβ166Updated last year
- Simple examples using Argilla tools to build AIβ53Updated 4 months ago
- Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"β200Updated 4 months ago
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agentsβ121Updated 9 months ago
- β144Updated 2 weeks ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.β168Updated 2 months ago
- WebLINX is a benchmark for building web navigation agents with conversational capabilitiesβ144Updated last month
- Mixing Language Models with Self-Verification and Meta-Verificationβ102Updated 3 months ago
- β374Updated 2 months ago
- Evaluating LLMs with CommonGen-Liteβ89Updated last year
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)β74Updated this week
- Source code for our paper: "SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals".β66Updated 8 months ago