{"total":18,"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":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54,"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":"2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","created":"2026-08-19","cited_by_count":12,"area":"synth"},{"id":"2509.04575","title":"Bootstrapping Task Spaces for Self-Improvement","created":"2025-09-04","cited_by_count":10,"area":"synth"},{"id":"2604.20209","title":"Scaling Self-Play with Self-Guidance","created":"2026-04-22","cited_by_count":10,"area":"synth"},{"id":"2512.07175","title":"SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models","created":"2025-12-08","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":"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":"2603.24202","title":"A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula","created":"2026-03-25","cited_by_count":3,"area":"synth"},{"id":"2608.02139","title":"Self-Improving Large Language Models via Progressive Experience Evolution","created":"2026-08-03","cited_by_count":2,"area":"synth"},{"id":"2608.20290","title":"Phantom Gains: Auditing Self-Improvement Against a Measured Null","created":"2026-08-20","cited_by_count":2,"area":"synth"},{"id":"2609.27389","title":"EvoAudio: Recursive Self-Improvement for Audio Understanding","created":"2026-09-23","cited_by_count":2,"area":"synth"},{"id":"2609.33398","title":"COEVO: Co-Evolving Context and Parameters for Recursive Self-Improvement","created":"2026-09-27","cited_by_count":0,"area":"synth"},{"id":"2609.34205","title":"Learning to Optimize through Solver-Grounded Self-Play","created":"2026-09-28","cited_by_count":0,"area":"synth"},{"id":"2609.35954","title":"ROSS: Relearning from Self-Generated Rollouts through Selective Supervision","created":"2026-09-28","cited_by_count":0,"area":"synth"},{"id":"2609.36750","title":"Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving","created":"2026-09-29","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}