{"total":32,"rows":[{"id":"2606.12370","title":"Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling","created":"2026-06-10","cited_by_count":9,"area":null},{"id":"2608.01662","title":"LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.30386","title":"DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving","created":"2026-08-31","cited_by_count":2,"area":null},{"id":"2606.19605","title":"FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.10836","title":"Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning","created":"2026-07-12","cited_by_count":1,"area":null},{"id":"2608.20634","title":"AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2609.13443","title":"Learning to Solve Hard Problems in RL for LLMs by Never Giving Up","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2606.05563","title":"SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.25451","title":"Learning with a Single Rollout via Pass@k Policy Optimization","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.08317","title":"Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.08837","title":"Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.11849","title":"AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.06933","title":"Ask-E: An Environment for Calibrated Question Generation","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.00062","title":"RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.08966","title":"Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.10712","title":"An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.12419","title":"MInTRL: Off-policy Intervention can boost On-policy RL","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.23989","title":"ACLArena: Agent Continue Learning in Multi-stage Post-training","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.28560","title":"Speculative Evaluation of Stochastic LLMs","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.31009","title":"G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33271","title":"Next Thoughts Are Distributions: Generative Autoregressive Reasoning in the Latent Space","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33559","title":"Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33642","title":"Learning to Learn from Context: Synthetic Training from Perturbed Public Documents","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35561","title":"RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35606","title":"TCSAlgBench: Benchmarking Automated Proving for Research-Level Theoretical Computer Science","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36116","title":"Dyad: Extending Large Language Models with Native Typed Decision-Making","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36860","title":"IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39927","title":"AdaGEPA: Adaptive Feedback Allocation for Reflective Prompt Optimization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03548","title":"Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.12367","title":"Which Skill to Distill? SGUID: Selecting a Compact Skill Bank for Model-Skill Co-Evolution","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12659","title":"MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.18301","title":"A dataset of formalised theorem statements from the Annals of Mathematics","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}