SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation

• URL: http://arxiv.org/abs/2603.16161v1
• Date: Tue, 17 Mar 2026 06:26:36 GMT
• Title: SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation
• Abstract summary: We propose a framework featuring a universal two-tiered reward mechanism designed to provide effective trajectory-level evaluation and dense step-level signals.<n>In traditional paradigms, rewards are determined solely by the final-turn feedback, which ignores the intermediate process and leads to ambiguous credit evaluation.<n>We show that our approach outperforms SOTA Arctic-Text2-R1-7B on BIRD 2.0 using identical models, propelling Text-to-reward convergence toward a robust multi-turn agent paradigm.
• Score: 51.696027315573296
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic Reinforcement Learning (RL) shows promise for complex tasks, but Text-to-SQL remains mostly restricted to single-turn paradigms. A primary bottleneck is the credit assignment problem. In traditional paradigms, rewards are determined solely by the final-turn feedback, which ignores the intermediate process and leads to ambiguous credit evaluation. To address this, we propose Agentic SQL, a framework featuring a universal two-tiered reward mechanism designed to provide effective trajectory-level evaluation and dense step-level signals. First, we introduce Aggregated Trajectory Reward (ATR) to resolve multi-turn credit assignment. Using an asymmetric transition matrix, ATR aggregates process-oriented scores to incentivize continuous improvement. Leveraging Lyapunov stability theory, we prove ATR acts as an energy dissipation operator, guaranteeing a cycle-free policy and monotonic convergence. Second, Column-Set Matching Reward (CSMR) provides immediate step-level rewards to mitigate sparsity. By executing queries at each turn, CSMR converts binary (0/1) feedback into dense [0, 1] signals based on partial correctness. Evaluations on BIRD show a 5% gain over binary-reward GRPO. Notably, our approach outperforms SOTA Arctic-Text2SQL-R1-7B on BIRD and Spider 2.0 using identical models, propelling Text-to-SQL toward a robust multi-turn agent paradigm.

Related papers

• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning [58.76655851910778]
  AgentOPSD is a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning.<n>We evaluate AgentOPSD on ALFWorld, WebShop, and Search-QA using Qwen2.5 models at two scales (3B and 7B)
  arXiv  Detail & Related papers  (2026-08-06T13:00:59Z)
• ARCO: Adaptive Rubric with Co-Evolution for Multi-Step LLM-Based Agents [12.091072999307622]
  ARCO is an adaptive rubric framework for reinforcement learning.<n>It improves the best EM in every setting over strong outcome-, rubric-, and process-reward baselines.<n>Its rubrics are step-specific, robust to design choices, and useful for diagnosing agent behavior.
  arXiv  Detail & Related papers  (2026-06-19T09:38:02Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning [14.508049757681862]
  LLM-powered coding agents spend the majority of their token budget reading repository files.<n>We show that this formulation creates a modeling bottleneck.<n>We propose LaMR, a structured pruning framework that decomposes code relevance into two interpretable quality dimensions.
  arXiv  Detail & Related papers  (2026-05-14T18:30:10Z)
• Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach [8.202508647749125]
  Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to extend their existing knowledge by dynamically incorporating external information.<n>Standard pipelines address this via a retrieve-then-select strategy, typically retaining only the top-k chunks based on relevance.<n>We propose MergeRAG, a novel framework that shifts the paradigm from static filtering to query-aware synthesis.
  arXiv  Detail & Related papers  (2026-03-18T09:09:52Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute [0.0]
  We empirically analyze the ARC Prize TRM checkpoint on ARC-AGI-1.<n>We show that test-time augmentation and majority-vote ensembling account for a substantial fraction of reported performance.<n>We also compare TRM with a naive QLoRA fine-tune of Llama 3 8B on canonical ARC-AGI-1.
  arXiv  Detail & Related papers  (2025-12-04T06:20:44Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards [48.321707628011005]
  Lookahead Tree-Based Rollouts (LATR) is a novel rollout strategy designed to explicitly promote trajectory-level diversity.<n>LATR accelerates policy learning by 131% on average and improves final pass@1 performance by 4.2%.
  arXiv  Detail & Related papers  (2025-10-28T11:12:02Z)
• Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data [38.656987194921854]
  Transformer (RT) architecture can be pretrained on diverse relational databases.<n>RT churns strong zero-shot, averaging 93% of fully supervised AUROC on binary classification tasks.
  arXiv  Detail & Related papers  (2025-10-07T18:51:51Z)
• SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval [4.230223288110963]
  Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image given a reference image and a relative text, without relying on costly triplet annotations.<n>Existing CLIP-based methods face two core challenges: (1) union-based feature fusion indiscriminately aggregates all visual cues, carrying over irrelevant background details that dilute the intended modification, and (2) global cosine similarity from CLIP embeddings lacks the ability to resolve fine-grained semantic relations.
  arXiv  Detail & Related papers  (2025-09-30T09:41:52Z)
• Semi-DETR: Semi-Supervised Object Detection with Detection Transformers [105.45018934087076]
  We analyze the DETR-based framework on semi-supervised object detection (SSOD) We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector. Our method outperforms all state-of-the-art methods by clear margins.
  arXiv  Detail & Related papers  (2023-07-16T16:32:14Z)
• End-to-End Lane detection with One-to-Several Transformer [6.79236957488334]
  O2SFormer converges 12.5x faster than DETR for the ResNet18 backbone. O2SFormer with ResNet50 backbone achieves 77.83% F1 score on CULane dataset, outperforming existing Transformer-based and CNN-based detectors.
  arXiv  Detail & Related papers  (2023-05-01T06:07:11Z)
• Automatically Generating Counterfactuals for Relation Exaction [18.740447044960796]
  relation extraction (RE) is a fundamental task in natural language processing. Current deep neural models have achieved high accuracy but are easily affected by spurious correlations. We develop a novel approach to derive contextual counterfactuals for entities.
  arXiv  Detail & Related papers  (2022-02-22T04:46:10Z)

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.