{"total":32,"rows":[{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54,"area":"synth"},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2502.11102","title":"OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling","created":"2025-02-16","cited_by_count":49,"area":"synth"},{"id":"2502.11741","title":"SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL","created":"2025-02-17","cited_by_count":19,"area":"synth"},{"id":"2509.07666","title":"MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval","created":"2025-09-06","cited_by_count":17,"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":"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":"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":"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":"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":"2604.20051","title":"Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text","created":"2026-04-21","cited_by_count":5,"area":"synth"},{"id":"2503.02878","title":"Language Models can Self-Improve at State-Value Estimation for Better Search","created":"2025-03-04","cited_by_count":4,"area":"synth"},{"id":"2503.06868","title":"Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation","created":"2025-03-10","cited_by_count":3,"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":"2601.06086","title":"AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning","created":"2025-12-31","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":"2505.08905","title":"Grounding Synthetic Data Evaluations of Language Models in Unsupervised Document Corpora","created":"2025-05-13","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":"2511.01490","title":"Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning","created":"2025-11-03","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":"2506.17637","title":"Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation","created":"2025-06-21","cited_by_count":0,"area":"synth"},{"id":"2511.01183","title":"QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code","created":"2025-11-03","cited_by_count":0,"area":"synth"},{"id":"2602.00665","title":"Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation","created":"2026-01-31","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":"2605.14062","title":"Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection","created":"2026-05-13","cited_by_count":0,"area":"synth"},{"id":"2606.18235","title":"EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation","created":"2026-06-16","cited_by_count":0,"area":"synth"},{"id":"2609.11146","title":"The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems","created":"2026-09-10","cited_by_count":0,"area":"synth"},{"id":"2610.01493","title":"No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse","created":"2026-10-01","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"}],"next_cursor":null}