Enhancing Planning Abilities in LLM-Based Agents: The AGENTGEN Approach

Generation Constraint Scaling Can Mitigate Hallucination

Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach

Diffusion Augmented Agents: A New Frontier in Efficient Exploration and Transfer Learning

OpenDevin: A New Frontier for AI Software Developers

AI and the International Mathematical Olympiad

Recursive Introspection: Teaching Language Model Agents How to Self-Improve

Context Embeddings for Efficient Answer Generation in RAG

Beyond Euclid: A New Frontier in Machine Learning

NeedleBench: Testing the Limits of LLMs in Long-Context Retrieval and Reasoning

Does Refusal Training in LLMs Generalize to the Past Tense?

SPREADSHEETLLM: Encoding Spreadsheets for Large Language Models

Research | Development | Consultation