{"total":17,"rows":[{"id":"2508.03613","title":"Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction","created":"2025-08-05","cited_by_count":154,"area":"synth"},{"id":"2605.31433","title":"SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks","created":"2026-05-29","cited_by_count":7,"area":"synth"},{"id":"2410.02992","title":"Learning to Better Search with Language Models via Guided Reinforced Self-Training","created":"2024-10-03","cited_by_count":5,"area":"synth"},{"id":"2510.16552","title":"LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs","created":"2025-10-18","cited_by_count":5,"area":"synth"},{"id":"2608.12486","title":"DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution","created":"2026-08-12","cited_by_count":5,"area":"synth"},{"id":"2603.15957","title":"GASP: Guided Asymmetric Self-Play For Coding LLMs","created":"2026-03-16","cited_by_count":4,"area":"synth"},{"id":"2603.18620","title":"Learning to Self-Evolve","created":"2026-03-19","cited_by_count":4,"area":"synth"},{"id":"2606.04507","title":"Self-Evolving Deep Research via Joint Generation and Evaluation","created":"2026-06-03","cited_by_count":2,"area":"synth"},{"id":"2603.24709","title":"Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards","created":"2026-03-25","cited_by_count":1,"area":"synth"},{"id":"2603.25118","title":"AnyDoc: Enhancing Document Generation via Large-Scale HTML/CSS Data Synthesis and Height-Aware Reinforcement Optimization","created":"2026-03-26","cited_by_count":1,"area":"synth"},{"id":"2604.18027","title":"CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora","created":"2026-04-20","cited_by_count":1,"area":"synth"},{"id":"2605.08138","title":"DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis","created":"2026-05-02","cited_by_count":1,"area":"synth"},{"id":"2605.08472","title":"Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models","created":"2026-05-08","cited_by_count":1,"area":"synth"},{"id":"2608.06474","title":"WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader","created":"2026-08-06","cited_by_count":1,"area":"synth"},{"id":"2609.09957","title":"Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models","created":"2026-09-09","cited_by_count":0,"area":"synth"},{"id":"2609.16059","title":"Towards Scalable RLVR: Multimodal Instruction Following Data Synthesis and Distillation","created":"2026-09-13","cited_by_count":0,"area":"synth"},{"id":"2609.36945","title":"Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamics, Convergence Rates, and Benefits of Off-Policyness","created":"2026-09-29","cited_by_count":0,"area":"synth"}],"next_cursor":null}