{"total":33,"rows":[{"id":"2509.07414","title":"Language Self-Play For Data-Free Training","created":"2025-09-09","cited_by_count":43,"area":"synth"},{"id":"2507.10628","title":"GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning","created":"2025-07-14","cited_by_count":34,"area":"synth"},{"id":"2509.15155","title":"Self-Improving Embodied Foundation Models","created":"2025-09-18","cited_by_count":32,"area":"synth"},{"id":"2607.15524","title":"Recursive Harness Self-Improvement","created":"2026-07-17","cited_by_count":32,"area":"synth"},{"id":"2503.00735","title":"LADDER: Self-Improving LLMs Through Recursive Problem Decomposition","created":"2025-03-02","cited_by_count":25,"area":"synth"},{"id":"2509.00375","title":"Open Data Synthesis For Deep Research","created":"2025-08-30","cited_by_count":16,"area":"synth"},{"id":"2506.07570","title":"OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization","created":"2025-06-09","cited_by_count":14,"area":"synth"},{"id":"2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","created":"2026-08-19","cited_by_count":12,"area":"synth"},{"id":"2605.29847","title":"EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation","created":"2026-05-28","cited_by_count":11,"area":"synth"},{"id":"2509.04575","title":"Bootstrapping Task Spaces for Self-Improvement","created":"2025-09-04","cited_by_count":10,"area":"synth"},{"id":"2607.28568","title":"Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering","created":"2026-07-30","cited_by_count":8,"area":"synth"},{"id":"2503.12303","title":"Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition","created":"2025-03-16","cited_by_count":7,"area":"synth"},{"id":"2510.16657","title":"Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence","created":"2025-10-18","cited_by_count":6,"area":"synth"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"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":"2506.08646","title":"TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning","created":"2025-06-10","cited_by_count":4,"area":"synth"},{"id":"2509.15568","title":"LiteLong: Resource-Efficient Long-Context Data Synthesis for LLMs","created":"2025-09-19","cited_by_count":3,"area":"synth"},{"id":"2501.18962","title":"Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping","created":"2025-01-31","cited_by_count":2,"area":"synth"},{"id":"2505.16927","title":"Latent Principle Discovery for Language Model Self-Improvement","created":"2025-05-22","cited_by_count":2,"area":"synth"},{"id":"2505.11533","title":"A Data Synthesis Method Driven by Large Language Models for Proactive Mining of Implicit User Intentions in Tourism","created":"2025-05-14","cited_by_count":1,"area":"synth"},{"id":"2505.17671","title":"MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis","created":"2025-05-23","cited_by_count":0,"area":"synth"},{"id":"2506.12161","title":"Meta-Learning and Synthetic Data for Automated Pretraining and Finetuning","created":"2025-06-11","cited_by_count":0,"area":"synth"},{"id":"2508.07598","title":"Keyword-Centric Prompting for One-Shot Event Detection with Self-Generated Rationale Enhancements","created":"2025-08-11","cited_by_count":0,"area":"synth"},{"id":"2510.18257","title":"DelvePO: Direction-Guided Self-Evolving Framework for Flexible Prompt Optimization","created":"2025-10-21","cited_by_count":0,"area":"synth"},{"id":"2511.07982","title":"NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation","created":"2025-11-11","cited_by_count":0,"area":"synth"},{"id":"2602.10014","title":"A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula","created":"2026-02-10","cited_by_count":0,"area":"synth"},{"id":"2603.18073","title":"Continually self-improving AI","created":"2026-03-18","cited_by_count":0,"area":"synth"},{"id":"2604.18639","title":"Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning","created":"2026-04-19","cited_by_count":0,"area":"synth"},{"id":"2605.16379","title":"An Information-Theoretic Criterion for Efficient Data Synthesis","created":"2026-05-11","cited_by_count":0,"area":"synth"},{"id":"2610.00779","title":"Effective Synthetic Data Curation Requires Group-Level Signals","created":"2026-09-30","cited_by_count":0,"area":"synth"},{"id":"2610.10623","title":"Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models","created":"2026-10-07","cited_by_count":0,"area":"synth"},{"id":"2610.13995","title":"GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games","created":"2026-09-26","cited_by_count":0,"area":"synth"}],"next_cursor":null}