{"total":55,"rows":[{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54,"area":"synth"},{"id":"2509.00375","title":"Open Data Synthesis For Deep Research","created":"2025-08-30","cited_by_count":16,"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":"2609.11873","title":"The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement","created":"2026-09-10","cited_by_count":11,"area":"synth"},{"id":"2607.22529","title":"Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills","created":"2026-07-24","cited_by_count":10,"area":"synth"},{"id":"2505.20166","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","created":"2025-05-26","cited_by_count":7,"area":"synth"},{"id":"2508.06635","title":"Valid Inference with Imperfect Synthetic Data","created":"2025-08-08","cited_by_count":7,"area":"synth"},{"id":"2509.23067","title":"Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks","created":"2025-09-27","cited_by_count":7,"area":"synth"},{"id":"2602.09877","title":"The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies","created":"2026-02-10","cited_by_count":7,"area":"synth"},{"id":"2605.26097","title":"Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay","created":"2026-05-25","cited_by_count":7,"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":"2505.15392","title":"Understanding the Anchoring Effect of LLM with Synthetic Data: Existence, Mechanism, and Potential Mitigations","created":"2025-05-21","cited_by_count":6,"area":"synth"},{"id":"2604.00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","created":"2026-04-01","cited_by_count":6,"area":"synth"},{"id":"2607.01480","title":"Procedural Memory Distillation: Online Reflection for Self-Improving Language Models","created":"2026-07-01","cited_by_count":6,"area":"synth"},{"id":"2607.01709","title":"COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows","created":"2026-07-02","cited_by_count":6,"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":"2509.21451","title":"VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding","created":"2025-09-25","cited_by_count":4,"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":"2607.24300","title":"Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents","created":"2026-07-27","cited_by_count":4,"area":"synth"},{"id":"2511.12063","title":"TextBO: Bayesian Optimization in Language Space for Eval-Efficient Self-Improving AI","created":"2025-11-15","cited_by_count":3,"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":"2601.09713","title":"LLM-Driven Preference Data Synthesis for Proactive Prediction of the Next User Utterance in Human-Machine Dialogue","created":"2025-12-24","cited_by_count":2,"area":"synth"},{"id":"2602.21218","title":"EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors","created":"2026-01-31","cited_by_count":2,"area":"synth"},{"id":"2603.03297","title":"TTSR: Test-Time Self-Evolving via Reflection","created":"2026-02-06","cited_by_count":2,"area":"synth"},{"id":"2605.13369","title":"Query-Conditioned Test-Time Self-Training for Large Language Models","created":"2026-05-13","cited_by_count":2,"area":"synth"},{"id":"2608.27287","title":"Astar: Learning to Propose Evolution Directions for Self-Evolving Industrial AI Systems","created":"2026-08-27","cited_by_count":2,"area":"synth"},{"id":"2601.04875","title":"EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis","created":"2026-01-08","cited_by_count":1,"area":"synth"},{"id":"2602.05145","title":"TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference","created":"2026-02-05","cited_by_count":1,"area":"synth"},{"id":"2602.23620","title":"Synthetic Data Powers Product Retrieval for Long-tail Knowledge-Intensive Queries in E-commerce Search","created":"2026-02-27","cited_by_count":1,"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":"2605.25572","title":"PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation","created":"2026-05-25","cited_by_count":1,"area":"synth"},{"id":"2606.03509","title":"EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation","created":"2026-06-02","cited_by_count":1,"area":"synth"},{"id":"2607.11883","title":"Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data","created":"2026-07-13","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":"2601.09734","title":"From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis","created":"2025-12-31","cited_by_count":0,"area":"synth"},{"id":"2601.11792","title":"A self-evolving multi-role collaborative framework with fine-grained difficulty guidance for innovative mathematical problem generation","created":"2026-01-16","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":"2603.09231","title":"Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness","created":"2026-03-10","cited_by_count":0,"area":"synth"},{"id":"2604.20933","title":"IRIS: Interpolative R\\'enyi Iterative Self-play for Large Language Model Fine-Tuning","created":"2026-04-22","cited_by_count":0,"area":"synth"},{"id":"2606.04238","title":"Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data","created":"2026-06-02","cited_by_count":0,"area":"synth"},{"id":"2606.32002","title":"Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA","created":"2026-06-30","cited_by_count":0,"area":"synth"},{"id":"2607.17139","title":"SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training","created":"2026-07-19","cited_by_count":0,"area":"synth"},{"id":"2608.08471","title":"Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production","created":"2026-08-09","cited_by_count":0,"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":"2609.34205","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":"2609.37132","title":"Train Ahead, Distill Back: Bootstrapping On-Policy Self-Distillation for Large Language Models","created":"2026-09-29","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":"2610.07979","title":"Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents","created":"2026-10-06","cited_by_count":0,"area":"synth"},{"id":"2610.08093","title":"SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data Synthesis","created":"2026-10-06","cited_by_count":0,"area":"synth"},{"id":"2610.09239","title":"The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules","created":"2026-10-07","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":"2610.12855","title":"Mitigating Capability Degradation in LLM Self-Improvement via Representation Geometry Regularization","created":"2026-10-09","cited_by_count":0,"area":"synth"}],"next_cursor":null}