ConstrainedSQL: Training LLMs for Text2SQL via Constrained Reinforcement Learning

• URL: http://arxiv.org/abs/2511.09693v1
• Date: Fri, 14 Nov 2025 01:04:37 GMT
• Title: ConstrainedSQL: Training LLMs for Text2SQL via Constrained Reinforcement Learning
• Authors: Weiqin Chen, Nhan Huu Pham, Michael Robert Glass, Long Hai Vu, Gaetano Rossiello, Dharmashankar Subramanian, Santiago Paternain,
• Abstract summary: Inappropriate rewards can lead to reward hacking, where models exploit loopholes in the reward structure to achieve high scores without genuinely solving the task.<n>This work considers a constrained RL framework for Text2 that incorporates natural and interpretable reward and constraint signals, while dynamically balancing trade-offs among them during the training.
• Score: 8.845655178975841
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has demonstrated significant promise in enhancing the reasoning capabilities of Text2SQL LLMs, especially with advanced algorithms such as GRPO and DAPO. However, the performance of these methods is highly sensitive to the design of reward functions. Inappropriate rewards can lead to reward hacking, where models exploit loopholes in the reward structure to achieve high scores without genuinely solving the task. This work considers a constrained RL framework for Text2SQL that incorporates natural and interpretable reward and constraint signals, while dynamically balancing trade-offs among them during the training. We establish the theoretical guarantees of our constrained RL framework and our numerical experiments on the well-known Text2SQL datasets substantiate the improvement of our approach over the state-of-the-art RL-trained LLMs.

Related papers

• Towards Sample-Efficient and Stable Reinforcement Learning for LLM-based Recommendation [56.92367609590823]
  Long Chain-of-Thought (Long CoT) reasoning has shown promise in Large Language Models (LLMs)<n>We argue that Long CoT is inherently ill-suited for the sequential recommendation domain.<n>We propose RISER, a novel Reinforced Item Space Exploration framework for Recommendation.
  arXiv  Detail & Related papers  (2026-01-31T10:02:43Z)
• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation [52.62655622099456]
  We propose reinforcement learning with verifiable reference-based rewards (RLVRR)<n>Instead of checking the final answer, RLVRR extracts an ordered linguistic signal from high-quality references (i.e., reward chain)<n>In this way, RLVRR decomposes rewards into two dimensions: content, which preserves deterministic core concepts, and style, which evaluates adherence to stylistic properties.
  arXiv  Detail & Related papers  (2026-01-26T14:39:58Z)
• Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following [42.05102776289243]
  Reinforcement Learning (RL) has shown promise for aligning Large Language Models (LLMs) to follow instructions with various constraints.<n>We propose Hindsight instruction Replay (HiR), a novel sample-efficient RL framework for complex instruction following tasks.
  arXiv  Detail & Related papers  (2025-12-29T13:31:08Z)
• Reinforcement Learning on Pre-Training Data [55.570379963147424]
  We introduce Reinforcement Learning on Pre-Training data (R), a new training-time scaling paradigm for optimizing large language models (LLMs)<n>R enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL)<n>Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of R.
  arXiv  Detail & Related papers  (2025-09-23T17:10:40Z)
• ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs [32.13266235550995]
  Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs)<n>Inspired by observations from human learning, we introduce a RL technique that integrates verifiable outcomes with the model's own confidence estimates.
  arXiv  Detail & Related papers  (2025-09-22T13:00:35Z)
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use [78.29315418819074]
  We introduce VerlTool, a unified and modular framework that addresses limitations through systematic design principles.<n>Our framework formalizes ARLT as multi-turn trajectories with multi-modal observation tokens (text/image/video), extending beyond single-turn RLVR paradigms.<n>The modular plugin architecture enables rapid tool integration requiring only lightweight Python definitions.
  arXiv  Detail & Related papers  (2025-09-01T01:45:18Z)
• SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data [65.56911325914582]
  We propose Self-play Reinforcement Learning (SeRL) to bootstrap Large Language Models (LLMs) training with limited initial data.<n>The proposed SeRL yields results superior to its counterparts and achieves performance on par with those obtained by high-quality data with verifiable rewards.
  arXiv  Detail & Related papers  (2025-05-25T13:28:04Z)
• Reinforced Latent Reasoning for LLM-based Recommendation [92.56166822197919]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks.<n>Existing methods typically rely on fine-tuning with explicit chain-of-thought (CoT) data.<n>In this work, we explore an alternative approach that shifts from explicit CoT reasoning to compact, information-dense latent reasoning.
  arXiv  Detail & Related papers  (2025-05-25T11:03:45Z)
• Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward [16.47355258999193]
  Reinforcement learning (RL) has been widely adopted to enhance the performance of large language models (LLMs) on Text-to- tasks.<n>Existing methods often rely on execution-based or LLM-based Bradley-Terry reward models.<n>We propose a novel reward model framework for RL-based Text-to-score named Graph-Reward-RTM.
  arXiv  Detail & Related papers  (2025-05-18T11:53:01Z)
• Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL [13.215512957681185]
  Existing approaches often rely on handcrafted reasoning paths with inductive biases that can limit their overall effectiveness.<n>Motivated by the recent success of reasoning-enhanced models such as OpenAI o1, we propose a novel set of partial rewards tailored specifically for the Text-to- exploration task.<n>We demonstrate that RL-only training with our proposed rewards consistently achieves higher accuracy and superior generalization compared to supervised fine-tuning.
  arXiv  Detail & Related papers  (2025-03-29T17:29:30Z)
• Beyond Human Preferences: Exploring Reinforcement Learning Trajectory Evaluation and Improvement through LLMs [12.572869123617783]
  Reinforcement learning (RL) faces challenges in evaluating policy trajectories within intricate game tasks. PbRL presents a pioneering framework that capitalizes on human preferences as pivotal reward signals. We propose a LLM-enabled automatic preference generation framework named LLM4PG.
  arXiv  Detail & Related papers  (2024-06-28T04:21:24Z)
• LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying [71.86163159193327]
  Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertaining to pattern completion. We introduce LaGR, which uses this predictive ability of LLMs to propose solutions to tasks that have been partially completed by a primary reinforcement learning (RL) agent.
  arXiv  Detail & Related papers  (2023-08-21T02:07:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.