{"total":38,"rows":[{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"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":"2601.07606","title":"Proof of Time: A Benchmark for Evaluating Scientific Idea Judgments","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2601.11653","title":"AI Agents Need Memory Control Over More Context","created":"2026-01-15","cited_by_count":7,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2604.13064","title":"Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub","created":"2026-03-19","cited_by_count":5,"area":null},{"id":"2605.26321","title":"Anchor: Mitigating Artifact Drift in Agent Benchmark Generation","created":"2026-05-25","cited_by_count":5,"area":null},{"id":"2606.30306","title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","created":"2026-06-29","cited_by_count":5,"area":null},{"id":"2510.14826","title":"To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2606.08625","title":"From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2508.12473","title":"Standardization of Neuromuscular Reflex Analysis -- Role of Fine-Tuned Vision-Language Model Consortium and OpenAI gpt-oss Reasoning LLM Enabled Decision Support System","created":"2025-08-17","cited_by_count":3,"area":null},{"id":"2604.06111","title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2606.14516","title":"Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2504.07385","title":"SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA","created":"2025-04-10","cited_by_count":2,"area":null},{"id":"2505.10360","title":"FactsR: A Safer Method for Producing High Quality Healthcare Documentation","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2604.05987","title":"Flowr -- Scaling Up Retail Supply Chain Operations Through Agentic AI in Large Scale Supermarket Chains","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2604.18302","title":"Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2605.31086","title":"Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2606.11079","title":"VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2508.21394","title":"AI Compute Architecture and Evolution Trends","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2510.20641","title":"Integrating Machine Learning into Belief-Desire-Intention Agents: Current Advances and Open Challenges","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2601.06301","title":"Beyond BeautifulSoup: Benchmarking LLM-Powered Web Scraping for Everyday Users","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2603.12483","title":"Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2606.09800","title":"FASE: Fast Adaptive Semantic Entropy for Code Quality","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.12207","title":"Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2607.17751","title":"MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2509.20172","title":"Benchmarking Web API Integration Code Generation","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2602.00456","title":"Benchmarking Agents in Insurance Underwriting Environments","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2605.11378","title":"An Empirical Study of Automating Agent Evaluation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.25376","title":"KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance and Hierarchical Policy Composition","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.24598","title":"Toward Self-Evolution-Ready Workflow Harnesses: A Reversible Migration Path and Convertibility Taxonomy for Expert LLM Pipelines","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.12823","title":"Human-AI Agent Interaction as a Neuroplastic Training Environment","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.10030","title":"Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.26225","title":"Agent Mesh: Reliability Primitives for Non-Idempotent Agent Delegation - Identity Adequacy and Evidence Adequacy","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.27102","title":"LAAF: A Layered Accountability Architecture Framework for LLM Applications","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.04836","title":"RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.08161","title":"Symphony for Text Generation: Benchmarking Clinical Note Generation","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.15938","title":"The Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}