paper-with-me

홈 › Papers

SQL-Zero: Self-Evolving Text-to-SQL

2026-09-04 · Daniel Machado Pedrozo, Julia Soares Dollis, Bryan Lincoln Marques de Oliveira, Vinicius Alboneti Aguiar, Sávio Salvarino Teles de Oliveira, Telma Woerle de Lima Soares arxiv

Training a competitive Text-to-SQL agent usually depends on human-annotated natural-language/SQL pairs, which are expensive, domain-specific, and a bottleneck for scaling to new databases. We show it is possible to train a competitive solver with zero annotated pairs. We introduce SQL-Zero, a proposer-solver self-play in which a challenger and a solver start from the same base LLM and the only ground truth is execution against the database itself. The challenger generates SQL pairs calibrated to the solver's current difficulty (targeting "hard but solvable"), and both roles are updated with GRPO in alternating turns, with a template-level repetition penalty on the challenger to prevent diversity collapse. Training on BIRD databases with no labels, self-play improves over the zero-shot base on BIRD dev by 6.6 points at 3B and 7.3 points at 7B. It also scores higher than a matched control trained under the same recipe on human BIRD gold over the same databases, although an exact paired test does not resolve that margin. Transfer depends on scale: at 3B every iteration outperforms the base on unseen Spider databases and under lexical perturbation (Spider-Syn), where it also degrades less than the matched BIRD-gold control, whereas at 7B only the first iteration preserves transfer.

📄 PDF Abstract BibTeX arXiv:2609.04697

Code (2)

Tavish9/awesome-daily-AI-arxiv ★ 114
arxivsub/arXivSub_daily_arxiv ★ 4

Similar Papers 제목 키워드 기반

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

2026-03-10 · Zongxia Li, Hongyang Du, Chengsong Huang, Xiyang Wu 외 arxiv

Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention. While recent approaches have demonstra…

Multimodal Reasoning

Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration

2026-02-11 · Jinghan He, Junfeng Fang, Feng Xiong, Zijun Yao 외 arxiv

Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passive interaction with static image collecti…

R-Zero: Self-Evolving Reasoning LLM from Zero Data

2025-08-07 · Chengsong Huang, Wenhao Yu, Xiaoyang Wang, Hongming Zhang 외 arxiv

Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models…

Reinforcement Learning

EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation

2026-06-02 · Zuhao Ge, Xiaosong Jia, Chao Wu, Yuchen Zhou 외 arxiv

Building memory is essential for long-horizon planning in zero-shot embodied navigation. Detector-centric scene graphs often compress observations into sparse nodes, discarding fine-grained visual evidence and accumulati…

Zero-shot Generalization3D Reconstruction

Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics

2026-02-11 · Leheng Sheng, Wenchang Ma, Ruixin Hong, Xiang Wang 외 arxiv

Despite chain-of-thought (CoT) playing crucial roles in LLM reasoning, directly rewarding it is difficult: training a reward model demands heavy human labeling efforts, and static RMs struggle with evolving CoT distribut…