{"total":42,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2502.14074","title":"Investigating Non-Transitivity in LLM-as-a-Judge","created":"2025-02-19","cited_by_count":34,"area":"agents"},{"id":"2512.04388","title":"Learning to Orchestrate Agents in Natural Language with the Conductor","created":"2025-12-04","cited_by_count":23,"area":"agents"},{"id":"2509.26553","title":"Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling","created":"2025-09-30","cited_by_count":13,"area":"agents"},{"id":"2603.07980","title":"\\$OneMillion-Bench: How Far are Language Agents from Human Experts?","created":"2026-03-09","cited_by_count":13,"area":"agents"},{"id":"2411.13768","title":"Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture","created":"2024-11-21","cited_by_count":11,"area":"agents"},{"id":"2507.11633","title":"General Modular Harness for LLM Agents in Multi-Turn Gaming Environments","created":"2025-07-15","cited_by_count":11,"area":"agents"},{"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":"2509.22887","title":"Infusing Theory of Mind into Socially Intelligent LLM Agents","created":"2025-09-26","cited_by_count":8,"area":"agents"},{"id":"2601.10504","title":"DR-Arena: an Automated Evaluation Framework for Deep Research Agents","created":"2026-01-15","cited_by_count":6,"area":"agents"},{"id":"2512.00417","title":"CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency","created":"2025-11-29","cited_by_count":5,"area":"agents"},{"id":"2512.04416","title":"DataGovBench: Benchmarking LLM Agents for Real-World Data Governance Workflows","created":"2025-12-04","cited_by_count":4,"area":"agents"},{"id":"2601.05039","title":"FinDeepForecast: A Live Multi-Agent System for Benchmarking Deep Research Agents in Financial Forecasting","created":"2026-01-08","cited_by_count":4,"area":"agents"},{"id":"2601.02941","title":"SastBench: A Benchmark for Testing Agentic SAST Triage","created":"2026-01-06","cited_by_count":3,"area":"agents"},{"id":"2608.21156","title":"Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence","created":"2026-08-21","cited_by_count":3,"area":"agents"},{"id":"2604.26962","title":"DeepTutor: Towards Agentic Personalized Tutoring","created":"2026-04-10","cited_by_count":2,"area":"agents"},{"id":"2605.22564","title":"SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations","created":"2026-05-21","cited_by_count":2,"area":"agents"},{"id":"2607.09016","title":"SLBench: Evaluating How LLM Agents Follow Logical Relations in Skills","created":"2026-07-10","cited_by_count":2,"area":"agents"},{"id":"2607.18084","title":"WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2607.25398","title":"HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following","created":"2026-07-28","cited_by_count":2,"area":"agents"},{"id":"2608.00355","title":"CurveShift: Is Agent Progress Scalar? Separating Level from Shape","created":"2026-07-31","cited_by_count":2,"area":"agents"},{"id":"2511.20709","title":"DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents","created":"2025-11-24","cited_by_count":1,"area":"agents"},{"id":"2602.13543","title":"LiveNewsBench: Evaluating LLM Web Search Capabilities with Freshly Curated News","created":"2026-02-14","cited_by_count":1,"area":"agents"},{"id":"2605.24197","title":"A Sober Look at Agentic Misalignment in Automated Workflows","created":"2026-05-22","cited_by_count":1,"area":"agents"},{"id":"2605.05250","title":"Decision-aware User Simulation Agent for Evaluating Conversational Recommender Systems","created":"2026-05-05","cited_by_count":0,"area":"agents"},{"id":"2605.28360","title":"Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2605.29653","title":"PTCG-Bench: Can LLM Agents Master Pok\\'emon Trading Card Game?","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2606.14155","title":"Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2607.04576","title":"Progressive Disclosure for LLM-Maintained Wiki Knowledge Bases: a Preregistered Ablation","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.14408","title":"Reward-Free Evolving Agents via Pairwise Validator","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2607.20645","title":"Frontier Financial Judgement: Can agents tell what might move a stock?","created":"2026-07-22","cited_by_count":0,"area":"agents"},{"id":"2608.14270","title":"TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments","created":"2026-08-14","cited_by_count":0,"area":"agents"},{"id":"2609.14239","title":"CoArena: Evaluating Computer-Use and Multi-Agent Systems in Real Time","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.16487","title":"Skill-based Agentic Evaluation for Real-time Data Science Tasks","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.19617","title":"DataCanvas-EDU: An Agentic Framework for Instructor-Guided Synthetic Data Generation in Business Analytics Education","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.21325","title":"LEGIT: Credentialing Protocol for Trustworthy AI Agent Marketplaces","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.29465","title":"SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.32227","title":"OptiArena: Can LLMs Improve Executable Algorithms under Fixed Resource Budgets?","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.36556","title":"MAADBench: The Refreshable Paradigm for Anomaly Detection in Multi-Agent Systems","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.19433","title":"EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}