3

Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL

Text-to-SQL with DeepSeek R1-style GRPO reinforcement learning post-training (arXiv preprint).

Mohammadreza Pourreza, Shayan Talaei, Ruoxi Sun, Xingchen Wan, Hailong Li, Azalia Mirhoseini, Amin Saberi, Sercan Ö. Arık

Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

Automatically discovering performant multi-agent systems end-to-end. (arXiv preprint)

Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulić, Anna Korhonen, Sercan Ö. Arık

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models

Overcoming RAG imperfections and knowledge conflicts with debating and reconcilation (arXiv preprint).

Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, Sercan Ö. Arık

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models