{"total":94,"rows":[{"id":"2606.14249","title":"HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry","created":"2026-06-12","cited_by_count":47,"area":null},{"id":"2606.11926","title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","created":"2026-06-10","cited_by_count":22,"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":"2606.05922","title":"Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference","created":"2026-06-04","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":"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":"2608.27454","title":"WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution","created":"2026-08-27","cited_by_count":12,"area":null},{"id":"2609.00196","title":"WHALE: A Simple Recipe for Joint Harness-Weight Optimization","created":"2026-08-31","cited_by_count":11,"area":null},{"id":"2606.04455","title":"The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?","created":"2026-06-03","cited_by_count":9,"area":null},{"id":"2604.18543","title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","created":"2026-04-20","cited_by_count":8,"area":null},{"id":"2606.12344","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks","created":"2026-06-10","cited_by_count":8,"area":null},{"id":"2605.10870","title":"Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2609.17523","title":"ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents","created":"2026-09-15","cited_by_count":7,"area":null},{"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":"2607.14004","title":"Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0","created":"2026-07-15","cited_by_count":6,"area":null},{"id":"2607.18235","title":"Automated Discovery Has No Universally Superior Harness","created":"2026-07-20","cited_by_count":6,"area":null},{"id":"2608.12629","title":"CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution","created":"2026-08-12","cited_by_count":5,"area":null},{"id":"2608.20169","title":"Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection","created":"2026-08-20","cited_by_count":5,"area":null},{"id":"2608.13417","title":"Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development","created":"2026-08-13","cited_by_count":4,"area":null},{"id":"2608.26530","title":"PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents","created":"2026-08-27","cited_by_count":4,"area":null},{"id":"2604.05912","title":"FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.10820","title":"MaD Physics: Evaluating information seeking under constraints in physical environments","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2605.21516","title":"Harnesses for Inference-Time Alignment over Execution Trajectories","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.22505","title":"Towards Direct Evaluation of Harness Optimizers via Priority Ranking","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2605.30219","title":"When Should Models Change Their Minds? Contextual Belief Management in Large Language Models","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.02863","title":"Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.09774","title":"Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2607.08332","title":"X-Alpha: An AI Quant Researcher with Memory-Driven Self-Evolution","created":"2026-07-09","cited_by_count":2,"area":null},{"id":"2607.15272","title":"SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2609.06396","title":"MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves","created":"2026-09-06","cited_by_count":2,"area":null},{"id":"2604.15719","title":"Harnessing Pre-Resolution Signals for Future Prediction Agents","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2606.21005","title":"Building Agent Harnesses for Scientific Curation from Multimodal Sources","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2606.21138","title":"SEED: Simple ViT and Evolving Harness for Explainable Text Forgery Detection","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2606.31808","title":"Large Databases Need Small, Open-Weight Language Models","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.09819","title":"Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.10108","title":"MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.19047","title":"Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2608.24804","title":"StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.18366","title":"Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts","created":"2026-09-16","cited_by_count":1,"area":null},{"id":"2609.22682","title":"Self-Organizing Agent Teams Learn to Reason Together","created":"2026-09-19","cited_by_count":1,"area":null},{"id":"2609.28908","title":"Automatic Harness Evolution for Hardware Design Verification: Can LLMs Consolidate Gains Across Discovered Harnesses?","created":"2026-09-24","cited_by_count":1,"area":null},{"id":"2609.30967","title":"MoMHa: Multi-Objective Optimization of LLM Harnesses over Accuracy, Safety, and Tokens","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2609.37725","title":"Context Language Models","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2610.02826","title":"Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2610.08432","title":"EMHO: EMbodied Agent Harness Optimization via Experience Traces","created":"2026-10-06","cited_by_count":1,"area":null},{"id":"2610.10426","title":"CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution","created":"2026-10-07","cited_by_count":1,"area":null},{"id":"2606.28270","title":"Agent-Native Immune System: Architecture, Taxonomy, and Engineering","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.00733","title":"LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.05686","title":"Provably Efficient Self-Calibrating Quantum Fault Tolerance","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.07527","title":"DocAtlas: Long-Document Understanding as Mutable-State Interaction","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.13228","title":"Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.20664","title":"DreamBench-SWE: A Multi-Session Memory-Hygiene Benchmark for Software Agents","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.22830","title":"Beyond the Harness: End-to-End Optimization of Context Artifacts for Enterprise Text-to-SQL","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.15209","title":"Failure-Guided Co-Evolution of Prompts and Training Data","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.19664","title":"VideoResearcher: Self-Improving Tool Design for Long-Video Understanding","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.20844","title":"Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.22247","title":"CHART: A Harness-Rotation Curriculum for Harness-Robust Search Agents","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.29837","title":"PUBG Ally: A Conversational Embodied Agent as an AI Teammate","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30297","title":"Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.32391","title":"SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33123","title":"Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33411","title":"MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34126","title":"JET: Judge-Guided Evolution at Test Time for Agent Programs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35031","title":"PEAR: Progressive Evidence-Based AutoResearch for Industrial Search Systems","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35290","title":"EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning","created":"2026-09-28","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":"2609.35855","title":"Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36380","title":"LEGO-Anything: Coding Agents for 3D Scene Reconstruction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37834","title":"Mixture of Self-Improving Branches For Agent Harness Optimization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39544","title":"Growing an Agent/Prover Interface: Evolutionary Tool Design for Cost-Efficient Theorem Proving in Rocq and Lean","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39765","title":"MemCodex: Self-Programming Hierarchical Memory for Language Agents","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.40330","title":"Turbo Harness: Instance-Adaptive Harness Optimization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.40340","title":"EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00531","title":"Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01235","title":"Harness Annealing: Learning to Act with Less External Control","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02920","title":"HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence","created":"2026-10-02","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":"2610.03966","title":"ROAR: Unifying Runs across Heterogeneous AI-Driven Research Systems","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04862","title":"GitSwarm: Decentralized Compounding Inference","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05334","title":"AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05382","title":"Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05533","title":"What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.06274","title":"What May an Agent Change About Itself? A Containment Floor for Self-Configuring Agent Runtimes","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08902","title":"Agent Plasticity: Measuring Self-Improvement Through Experience","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.08995","title":"PhysEvo: Astra Can Act, Let It","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.13025","title":"Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13399","title":"RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13991","title":"Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.14625","title":"From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16966","title":"Learning to Design SR Solvers: Harness Optimization for Symbolic Regression","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17370","title":"HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18813","title":"Self-Evolving Agent Harness","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19184","title":"HERO: Harnessing Evidence for Test-time Refinement and Prompt Optimization in Program Generation","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20099","title":"EvalBuilder: Can LLMs Build Efficient Benchmarks?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}