Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL

• URL: http://arxiv.org/abs/2605.04719v2
• Date: Thu, 07 May 2026 02:33:36 GMT
• Title: Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQL
• Abstract summary: We propose FineStep, a novel framework for step-level credit assignment in tool-augmented Text-to-augmented Text.<n>We show that FineStep achieves state-of-the-art performance and reduces redundant tool interactions, with a 3.25% average EX gain over GRPO at the 4B scale.
• Score: 13.130554329857496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tool-integrated Text-to-SQL parsing has emerged as a promising paradigm, framing SQL generation as a sequential decision-making process interleaved with tool execution. However, existing reinforcement learning approaches mainly rely on coarse-grained outcome supervision, resulting in a fundamental credit assignment problem: models receive the same reward for any trajectory that yields the correct answer, even when intermediate steps are redundant, inefficient, or erroneous. Consequently, models are encouraged to explore suboptimal reasoning spaces, limiting both efficiency and generalization. To address this problem, we propose FineStep, a novel framework for step-level credit assignment in tool-augmented Text-to-SQL. First, we introduce a reward design with independent process rewards to alleviate the signal sparsity of outcome supervision. Next, we present a step-level credit assignment mechanism to precisely quantify the value of each reasoning step. Finally, we develop a policy optimization method based on step-level advantages for efficient updates. Extensive experiments on BIRD benchmarks show that FineStep achieves state-of-the-art performance and reduces redundant tool interactions, with a 3.25% average EX gain over GRPO at the 4B scale.

Related papers

• TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition [62.56752617853322]
  Outcome-based rewards provide only sparse feedback, while trajectory-supervised rewards depend on annotated reference solutions.<n>We propose TIER: Trajectory-Invariant Execution Rewards, a reward framework that derives supervision directly from function schemas and runtime execution.
  arXiv  Detail & Related papers  (2026-05-16T03:47:26Z)
• ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation [54.071574153853994]
  ProRAG is a process-supervised reinforcement learning framework designed to integrate learned step-level supervision into the online optimization loop.<n>Our framework consists of four stages: (1) Supervised Policy Warmup to initialize the model with a structured reasoning format; (2) construction of an MCTS-based Process Reward Model (PRM) to quantify intermediate reasoning quality; (3) PRM-Guided Reasoning Refinement to align the policy with fine-grained process preferences; and (4) Process-Supervised Reinforcement Learning with a dual-granularity advantage mechanism.
  arXiv  Detail & Related papers  (2026-01-29T16:04:59Z)
• MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL [46.37961458768655]
  Large language models (LLMs) are increasingly used in Text-to-aware tasks.<n>Existing methods rely on static execution feedback, which restricts real-time error correction.<n>We propose MTIR-IDER, an innovative Multi-turn Tool-Integrated Reasoning reinforcement learning framework.
  arXiv  Detail & Related papers  (2025-10-29T13:34:27Z)
• HES-SQL: Hybrid Reasoning for Efficient Text-to-SQL with Structural Skeleton Guidance [6.653834890554154]
  We present HES-, a novel hybrid training framework that advances Text-to-latency generation through the integration of thinking-mode-fused supervised fine-tuning.<n>This framework enables switch between reasoning and non-reasoning modes while improving query accuracy and execution efficiency.
  arXiv  Detail & Related papers  (2025-10-10T01:15:57Z)
• Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search [62.1546099504045]
  We propose a dual-phase test-time scaling framework that separates reasoning into planning and execution.<n>Specifically, we decompose reasoning trajectories and develop reward models for each phase, enabling the search to explore and prune plans and executions separately.<n> Experiments on both mathematical reasoning and code generation benchmarks demonstrate that our approach consistently improves accuracy while reducing computation redundant.
  arXiv  Detail & Related papers  (2025-09-29T19:27:23Z)
• Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling [11.577572131517714]
  State-of-the-art (SOTA) text-to-the-art methods still lag significantly behind human experts on challenging computation benchmarks like BIRD.<n>Current approaches that explore test-time scaling lack an orchestrated strategy and neglect the model's internal reasoning process.
  arXiv  Detail & Related papers  (2025-09-29T07:50:02Z)
• SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling [58.05959902776133]
  We introduce Single-Pass.<n>with Reference-Guided Evaluation (SPARE), a novel structured framework that enables efficient per-step annotation.<n>We demonstrate SPARE's effectiveness across four diverse datasets spanning mathematical reasoning (GSM8K, MATH), multi-hop question answering (MuSiQue-Ans), and spatial reasoning (SpaRP)<n>On ProcessBench, SPARE demonstrates data-efficient out-of-distribution generalization, using only $sim$16% of training samples compared to human-labeled and other synthetically trained baselines.
  arXiv  Detail & Related papers  (2025-06-18T14:37:59Z)
• DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal [55.13854171147104]
  Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development.<n>We present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents.<n>We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2.
  arXiv  Detail & Related papers  (2025-03-18T14:02:59Z)
• Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation [27.484259938667776]
  Large Language Models excel at code generation yet struggle with complex programming tasks that demand reasoning.<n>We introduce Outcome Refining Process Supervision, which unifies process and outcome supervision by leveraging executable verification.<n>Experiments across 5 models and 3 benchmarks show consistent gains, with 26.9% higher correctness and 42.2% improved code efficiency.
  arXiv  Detail & Related papers  (2024-12-19T17:59:42Z)
• Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning [75.74103236299477]
  Chain-of-thought prompting(CoT) and tool augmentation have been validated as effective practices for improving large language models. We propose a new approach that can deliberate the reasoning steps with tool interfaces, namely textbfDELI. Experimental results on CARP and six other datasets show that the proposed DELI mostly outperforms competitive baselines.
  arXiv  Detail & Related papers  (2023-06-04T17:02:59Z)

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.