{"total":27,"rows":[{"id":"2604.06126","title":"Gym-Anything: Turn any Software into an Agent Environment","created":"2026-04-07","cited_by_count":27,"area":"agents"},{"id":"2604.11978","title":"The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break","created":"2026-04-13","cited_by_count":25,"area":"agents"},{"id":"2512.10534","title":"Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning","created":"2025-12-11","cited_by_count":7,"area":"agents"},{"id":"2510.11004","title":"Automating Structural Engineering Workflows with Large Language Model Agents","created":"2025-10-13","cited_by_count":6,"area":"agents"},{"id":"2605.16116","title":"ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents","created":"2026-05-15","cited_by_count":5,"area":"agents"},{"id":"2604.25135","title":"FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments","created":"2026-04-28","cited_by_count":4,"area":"agents"},{"id":"2510.08317","title":"Iterated Agent for Symbolic Regression","created":"2025-10-09","cited_by_count":3,"area":"agents"},{"id":"2602.02751","title":"Scaling Small Agents Through Strategy Auctions","created":"2026-02-02","cited_by_count":3,"area":"agents"},{"id":"2606.29824","title":"Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering","created":"2026-06-29","cited_by_count":3,"area":"agents"},{"id":"2601.16649","title":"LUMINA: Long-horizon Understanding for Multi-turn Interactive Agents","created":"2026-01-23","cited_by_count":2,"area":"agents"},{"id":"2606.03698","title":"Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.08340","title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","created":"2026-06-06","cited_by_count":2,"area":"agents"},{"id":"2607.01087","title":"Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.02255","title":"AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents","created":"2026-07-02","cited_by_count":2,"area":"agents"},{"id":"2605.14563","title":"Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2605.30102","title":"When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems","created":"2026-05-28","cited_by_count":1,"area":"agents"},{"id":"2606.19613","title":"StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2606.22203","title":"When Is Emergent Consensus Real? A Measured Coupling Gain and a Validity Diagnostic for LLM Agent Societies","created":"2026-06-20","cited_by_count":1,"area":"agents"},{"id":"2606.31522","title":"FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2608.15654","title":"When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations","created":"2026-08-16","cited_by_count":1,"area":"agents"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2607.25369","title":"ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2608.29889","title":"VibeJam: A User Study Platform for Web Development with Agents","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.27321","title":"Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.36319","title":"StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.06069","title":"Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.19345","title":"When Is Smaller Greener? Right-Sizing Language Models for Agentic AI","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}