aymeric-roucher / GAIA
Beating the GAIA benchmark with Transformers Agents. π
β63Updated 3 weeks ago
Related projects β
Alternatives and complementary repositories for GAIA
- β103Updated 3 months ago
- π§ Compare how Agent systems perform on several benchmarks. ππβ47Updated last month
- Data preparation code for CrystalCoder 7B LLMβ42Updated 6 months ago
- Environments, tools, and benchmarks for general computer agentsβ172Updated last month
- LLM reads a paper and produce a working prototypeβ36Updated 2 weeks ago
- GPT-4 Level Conversational QA Trained In a Few Hoursβ55Updated 3 months ago
- Source code for our paper: "SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals".β65Updated 4 months ago
- β35Updated last year
- My implementation of "Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models"β92Updated last year
- Code repo for "Agent Instructs Large Language Models to be General Zero-Shot Reasoners"β82Updated 2 months ago
- β116Updated 5 months ago
- Evaluating LLMs with CommonGen-Liteβ85Updated 8 months ago
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)β65Updated this week
- Client Code Examples, Use Cases and Benchmarks for Enterprise h2oGPTe RAG-Based GenAI Platformβ81Updated this week
- CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/β192Updated last week
- β51Updated 4 months ago
- β37Updated 11 months ago
- Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agentsβ111Updated 5 months ago
- β42Updated 2 months ago
- Data preparation code for Amber 7B LLMβ84Updated 6 months ago
- β73Updated 10 months ago
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language Mβ¦β181Updated 3 weeks ago
- Pre-training code for CrystalCoder 7B LLMβ53Updated 6 months ago
- Source code of the paper: RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering [Fβ¦β58Updated 5 months ago
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absoluteβ¦β48Updated 4 months ago
- WebLINX is a benchmark for building web navigation agents with conversational capabilitiesβ118Updated last month
- β56Updated 3 weeks ago
- Experimental Code for StructuredRAG: Structured Outputs in Retrieval-Augmented Generationβ94Updated this week
- β41Updated last month