MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL
Large Language Models (LLMs) often struggle with the precise logic and schema alignment required for complex Text-to-SQL tasks. While current methods rely heavily on static prompting, they lack the ability to dynamically adapt and self-correct through environmental interaction. To bridge this gap, we propose MARS-SQL, a trainable multi-agent framework for Text-to-SQL. Rather than introducing a new standalone SQL primitive, MARS-SQL makes an agentic workflow trainable by decomposing the problem into three specialized roles: schema grounding, query generation, and solution validation. Central to our approach is a generation agent trained via a multi-turn RL policy within a ReAct-style loop. The agent learns to iteratively reason, execute intermediate SQL actions on a live database, and refine its strategy based on execution feedback. To improve robustness, we further introduce a validation mechanism that treats solution selection as a generative modeling task, identifying the optimal interaction trajectory through next-token prediction probabilities. Empirical evaluations demonstrate the effectiveness of coupling interactive learning with trajectory ranking. MARS-SQL achieves state-of-the-art performance, recording an execution accuracy of 77.84% on the BIRD development dataset and 89.75% on the Spider test dataset, while also transferring strongly to out-of-domain benchmarks. Code is available at https://github.com/YangHaolin0526/MARS-SQL.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-agent Reinforcement LearningResults from the Paper
| Rank | Task | Dataset | Model | Metrics |
|---|---|---|---|---|
| #5 | Text-To-SQL | spider | MARS-SQL | Execution Accuracy (Test): 89.75 |
Similar Papers 제목 키워드 기반
MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism
Recent progress in large language models (LLMs) has been propelled by reinforcement learning with verifiable rewards (RLVR) and test-time scaling. However, the limited output length of LLMs constrains the depth of reason…
Reinforcement LearningMARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
Reinforcement learning (RL) paradigms have demonstrated strong performance on reasoning-intensive tasks such as code generation. However, limited trajectory diversity often leads to diminishing returns, which constrains …
Reinforcement LearningCode GenerationMARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation
While the complex reasoning capability of Large Language Models (LLMs) has attracted significant attention, single-agent systems often encounter inherent performance ceilings in complex tasks such as code generation. Mul…
Multi-agent Reinforcement LearningCode GenerationSenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning
While Vision-Language Models (VLMs) can solve complex tasks through agentic reasoning, their capabilities remain largely constrained to text-oriented chain-of-thought or isolated tool invocation. They fail to exhibit the…
Reinforcement LearningVisual ReasoningImage CroppingMARS-Gym: A Gym framework to model, train, and evaluate Recommender Systems for Marketplaces
Recommender Systems are especially challenging for marketplaces since they must maximize user satisfaction while maintaining the healthiness and fairness of such ecosystems. In this context, we observed a lack of resourc…
FairnessRecommendation Systems