{"total":115,"rows":[{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","created":"2026-03-30","cited_by_count":309,"area":null},{"id":"2602.20133","title":"AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization","created":"2026-02-23","cited_by_count":60,"area":null},{"id":"2602.23413","title":"EvoX: Meta-Evolution for Automated Discovery","created":"2026-02-26","cited_by_count":60,"area":null},{"id":"2604.01658","title":"CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery","created":"2026-04-02","cited_by_count":52,"area":"agents"},{"id":"2602.11858","title":"Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception","created":"2026-02-12","cited_by_count":50,"area":"mllm"},{"id":"2602.10177","title":"Towards Autonomous Mathematics Research","created":"2026-02-10","cited_by_count":40,"area":null},{"id":"2601.21590","title":"Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening","created":"2026-01-29","cited_by_count":31,"area":"lr"},{"id":"2606.06473","title":"MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery","created":"2026-06-04","cited_by_count":28,"area":"synth"},{"id":"2602.02919","title":"DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution","created":"2026-02-02","cited_by_count":26,"area":null},{"id":"2602.19128","title":"K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model","created":"2026-02-22","cited_by_count":24,"area":"wm"},{"id":"2603.24517","title":"AVO: Agentic Variation Operators for Autonomous Evolutionary Search","created":"2026-03-25","cited_by_count":24,"area":"agents"},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"area":null},{"id":"2604.19341","title":"Structured Scaling of AI Discovery Across Diverse Scientific Domains","created":"2026-04-21","cited_by_count":21,"area":null},{"id":"2605.27276","title":"SIA: Self Improving AI with Harness & Weight Updates","created":"2026-05-26","cited_by_count":21,"area":null},{"id":"2607.15275","title":"RoboTTT: Context Scaling for Robot Policies","created":"2026-07-16","cited_by_count":19,"area":null},{"id":"2609.14858","title":"Dream-RSI: Recursive Self-Improvement through Evolving Worlds","created":"2026-09-14","cited_by_count":18,"area":null},{"id":"2605.08678","title":"MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI","created":"2026-05-09","cited_by_count":17,"area":null},{"id":"2604.12290","title":"Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization","created":"2026-04-14","cited_by_count":16,"area":"agents"},{"id":"2607.03935","title":"Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions","created":"2026-07-04","cited_by_count":12,"area":null},{"id":"2605.13821","title":"Harnessing Agentic Evolution","created":"2026-05-13","cited_by_count":11,"area":"agents"},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"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":"2605.08083","title":"LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling","created":"2026-05-08","cited_by_count":10,"area":"lr"},{"id":"2606.10402","title":"Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries","created":"2026-06-09","cited_by_count":10,"area":null},{"id":"2606.24530","title":"NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?","created":"2026-06-23","cited_by_count":10,"area":"agents"},{"id":"2603.02203","title":"Tool Verification for Test-Time Reinforcement Learning","created":"2026-03-02","cited_by_count":9,"area":"lr"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2603.11327","title":"Meta-Reinforcement Learning with Self-Reflection for Agentic Search","created":"2026-03-11","cited_by_count":8,"area":"agents"},{"id":"2603.23994","title":"Understanding the Challenges in Iterative Generative Optimization with LLMs","created":"2026-03-25","cited_by_count":8,"area":null},{"id":"2604.23472","title":"Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization","created":"2026-04-25","cited_by_count":8,"area":null},{"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":"2602.07276","title":"Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs","created":"2026-02-07","cited_by_count":7,"area":"mechinterp"},{"id":"2609.21032","title":"Scaling Discovery through Test-Time Communication","created":"2026-09-17","cited_by_count":7,"area":"agents"},{"id":"2603.28342","title":"Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization","created":"2026-03-30","cited_by_count":6,"area":null},{"id":"2606.13662","title":"EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery","created":"2026-06-11","cited_by_count":6,"area":"agents"},{"id":"2606.29082","title":"Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks","created":"2026-06-27","cited_by_count":6,"area":null},{"id":"2607.02807","title":"SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery","created":"2026-07-02","cited_by_count":6,"area":"agents"},{"id":"2607.18235","title":"Automated Discovery Has No Universally Superior Harness","created":"2026-07-20","cited_by_count":6,"area":null},{"id":"2602.07040","title":"Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2605.19269","title":"CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2606.02859","title":"Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2601.22313","title":"Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2602.15156","title":"Panini: Continual Learning in Token Space via Structured Memory","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2603.18620","title":"Learning to Self-Evolve","created":"2026-03-19","cited_by_count":4,"area":"synth"},{"id":"2604.02721","title":"GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning","created":"2026-04-03","cited_by_count":4,"area":"agents"},{"id":"2605.07039","title":"PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2606.01075","title":"On the Generalization Gap in Self-Evolving Language Model Reasoning","created":"2026-05-31","cited_by_count":4,"area":"lr"},{"id":"2608.00155","title":"AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?","created":"2026-07-31","cited_by_count":4,"area":"agents"},{"id":"2601.20379","title":"Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2604.00830","title":"Meta-TTL: Meta-Learning Self-Improvement Policies for Language Agents","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2604.18607","title":"TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2605.14477","title":"Test-Time Learning with an Evolving Library","created":"2026-05-14","cited_by_count":3,"area":null},{"id":"2605.20086","title":"What Do Evolutionary Coding Agents Evolve?","created":"2026-05-19","cited_by_count":3,"area":"agents"},{"id":"2606.04075","title":"Large Language Models Hack Rewards, and Society","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2606.23595","title":"SPIRAL: Learning to Search and Aggregate","created":"2026-06-22","cited_by_count":3,"area":"lr"},{"id":"2609.01679","title":"A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference","created":"2026-09-01","cited_by_count":3,"area":null},{"id":"2603.03297","title":"TTSR: Test-Time Self-Evolving via Reflection","created":"2026-02-06","cited_by_count":2,"area":"synth"},{"id":"2605.09018","title":"Evolving Ensemble of Agents","created":"2026-05-09","cited_by_count":2,"area":"agents"},{"id":"2605.13037","title":"MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning","created":"2026-05-13","cited_by_count":2,"area":"lr"},{"id":"2606.05253","title":"Alpha-RTL: Test-Time Training for RTL Hardware Optimization","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2606.28876","title":"MMLA: Memory-Mediated Learning Architecture for Predictive Dual-State Adaptation","created":"2026-06-27","cited_by_count":2,"area":null},{"id":"2606.31182","title":"AI-Assisted Discovery of Convex Relaxations via Dual Agents","created":"2026-06-30","cited_by_count":2,"area":"agents"},{"id":"2608.14441","title":"PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments","created":"2026-08-14","cited_by_count":2,"area":null},{"id":"2609.15309","title":"When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis","created":"2026-09-14","cited_by_count":2,"area":"lr"},{"id":"2602.03466","title":"Quantum Circuit Generation via test-time learning with large language models","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.07670","title":"Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.10233","title":"ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.09221","title":"Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2603.17683","title":"Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents","created":"2026-03-18","cited_by_count":1,"area":"agents"},{"id":"2603.28361","title":"Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2605.03808","title":"Agentic-imodels: Evolving agentic interpretability tools via autoresearch","created":"2026-05-05","cited_by_count":1,"area":"agents"},{"id":"2605.30015","title":"Test Time Training for Supervised Causal Learning","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.03544","title":"SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.11437","title":"The Power of Test-Time Training for Approximate Sampling","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.15197","title":"StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling","created":"2026-06-13","cited_by_count":1,"area":"lr"},{"id":"2608.08958","title":"Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods","created":"2026-08-09","cited_by_count":1,"area":"lr"},{"id":"2608.23691","title":"Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2609.38349","title":"MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2610.12002","title":"Agentic-TTT: Training test-time policy for test-time training","created":"2026-10-08","cited_by_count":1,"area":"agents"},{"id":"2602.18918","title":"Early Evidence of Vibe-Proving with Consumer LLMs: A Case Study on Spectral Region Characterization with ChatGPT-5.2 (Thinking)","created":"2026-02-21","cited_by_count":0,"area":"lr"},{"id":"2604.05716","title":"Can Large Language Models Reinvent Foundational Algorithms?","created":"2026-04-07","cited_by_count":0,"area":"safety"},{"id":"2605.05193","title":"Grokability in five inequalities","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.10716","title":"What should post-training optimize? A test-time scaling law perspective","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.11328","title":"Epistemic Uncertainty for Test-Time Discovery","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.22984","title":"Test-Time Training Undermines Safety Guardrails","created":"2026-05-21","cited_by_count":0,"area":"safety"},{"id":"2605.31464","title":"GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.18910","title":"REVES: REvision and VErification--Augmented Training for Test-Time Scaling","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2606.27369","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.26828","title":"Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2607.27726","title":"Baikal: Structured Search for Deep Research over Data Lakes","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2608.28660","title":"Test-Time Scaling for Scientific Equation Discovery","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2608.29305","title":"Learning Simple Test-Time Environments for LLM Web Agents","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2609.04141","title":"Efficient Test-Time Adaptation through Human-AI Interaction","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.25510","title":"Hill Sampling for Test-Time Scaling: A Simple and Better Alternative to Repeated Sampling, Evolution, and Training","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.30884","title":"CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters","created":"2026-09-25","cited_by_count":0,"area":"inference"},{"id":"2609.35704","title":"DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36393","title":"Reward-rate Policy Gradient for Efficient Machine Learning Engineering Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.38757","title":"Self-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy Optimization","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.39383","title":"From Search to Signal: Online Post-Training in Automatic Heuristic Design","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}