{"total":57,"rows":[{"id":"2510.00615","title":"ACON: Optimizing Context Compression for Long-horizon LLM Agents","created":"2025-10-01","cited_by_count":136,"area":"agents"},{"id":"2510.04851","title":"LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation","created":"2025-10-06","cited_by_count":40,"area":"agents"},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37,"area":"agents"},{"id":"2509.21766","title":"UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios","created":"2025-09-26","cited_by_count":26,"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":"2604.24964","title":"Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks","created":"2026-04-27","cited_by_count":21,"area":"agents"},{"id":"2608.25593","title":"JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution","created":"2026-08-26","cited_by_count":16,"area":"agents"},{"id":"2509.06733","title":"Reinforcement Learning Foundations for Deep Research Systems: A Survey","created":"2025-09-08","cited_by_count":14,"area":"lr"},{"id":"2603.22862","title":"The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration","created":"2026-03-24","cited_by_count":14,"area":"agents"},{"id":"2510.14621","title":"ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks","created":"2025-10-16","cited_by_count":10,"area":"agents"},{"id":"2512.13168","title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2602.05843","title":"OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2602.10525","title":"LHAW: Controllable Underspecification for Long-Horizon Tasks","created":"2026-02-11","cited_by_count":6,"area":null},{"id":"2606.15862","title":"RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments","created":"2026-06-14","cited_by_count":6,"area":"lr"},{"id":"2606.18543","title":"CEO-Bench: Can Agents Play the Long Game?","created":"2026-06-16","cited_by_count":6,"area":"agents"},{"id":"2607.20911","title":"Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2607.28956","title":"MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations","created":"2026-07-31","cited_by_count":6,"area":"agents"},{"id":"2512.24851","title":"VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation agents","created":"2025-12-31","cited_by_count":5,"area":"mllm"},{"id":"2602.02039","title":"Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models","created":"2026-02-02","cited_by_count":5,"area":"agents"},{"id":"2605.30434","title":"LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2510.15966","title":"PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency","created":"2025-10-12","cited_by_count":3,"area":null},{"id":"2602.02751","title":"Scaling Small Agents Through Strategy Auctions","created":"2026-02-02","cited_by_count":3,"area":"agents"},{"id":"2604.15715","title":"GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2606.05342","title":"SentinelBench: A Benchmark for Long-Running Monitoring Agents","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2601.20650","title":"OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks","created":"2026-01-28","cited_by_count":2,"area":"agents"},{"id":"2605.07339","title":"Tools as Continuous Flow for Evolving Agentic Reasoning","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2606.08340","title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","created":"2026-06-06","cited_by_count":2,"area":"agents"},{"id":"2607.27155","title":"OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2509.20900","title":"Learning to Summarize by Learning to Quiz: Adversarial Agentic Collaboration for Long Document Summarization","created":"2025-09-25","cited_by_count":1,"area":"agents"},{"id":"2601.21754","title":"Language-based Trial and Error Falls Behind in the Era of Experience","created":"2026-01-29","cited_by_count":1,"area":"agents"},{"id":"2602.02760","title":"From Task Solving to Robust Real-World Adaptation in LLM Agents","created":"2026-02-02","cited_by_count":1,"area":"agents"},{"id":"2603.16453","title":"RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments","created":"2026-03-17","cited_by_count":1,"area":"agents"},{"id":"2604.02522","title":"Opal: Private Memory for Personal AI","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2604.23455","title":"CUJBench: Benchmarking LLM-Agent on Cross-Modal Failure Diagnosis from Browser to Backend","created":"2026-04-25","cited_by_count":1,"area":"agents"},{"id":"2605.17324","title":"ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents","created":"2026-05-17","cited_by_count":1,"area":"agents"},{"id":"2606.21654","title":"ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks","created":"2026-06-19","cited_by_count":1,"area":"agents"},{"id":"2607.06008","title":"PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows","created":"2026-07-07","cited_by_count":1,"area":"agents"},{"id":"2607.19865","title":"DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2608.05263","title":"OrchestraBench: Evaluating Multi-Agent Orchestration Failure Modes, Recovery, and Decomposition Quality","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.26546","title":"DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows","created":"2026-08-27","cited_by_count":1,"area":"agents"},{"id":"2609.01056","title":"WorldBench: Culturally Grounded Benchmark for Multilingual Agents","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2609.15054","title":"BusMA: A Bus Communication Substrate for Multi-Agent Systems","created":"2026-09-14","cited_by_count":1,"area":"agents"},{"id":"2602.00456","title":"Benchmarking Agents in Insurance Underwriting Environments","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2606.10956","title":"Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.14397","title":"Running the Gauntlet: Challenging Agentic Tasks","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2606.26346","title":"How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2607.01245","title":"Office Comprehension Benchmark","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.05139","title":"Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.18050","title":"StagedWorkspace: A Versioned Workspace for Knowledge-Work Agents","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2609.04556","title":"Rhythms of Work: Multi-Scale Interpretation of Human Behavioral Traces for Workplace Agents","created":"2026-09-03","cited_by_count":0,"area":"agents"},{"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":"2609.30604","title":"The Hard Part Comes After Search: Benchmarking Web Agents on Synthesizing, Organizing, and Displaying Knowledge","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.31906","title":"EmailBench: A Benchmark for Evaluating LLM Agents on Enterprise Email and Productivity Tasks","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2610.16117","title":"Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.18603","title":"AgentStripes: An Evidence-Graded Maturity Model for AI Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}