{"total":29,"rows":[{"id":"2505.16944","title":"AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios","created":"2025-05-22","cited_by_count":49,"area":"agents"},{"id":"2604.20006","title":"From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents","created":"2026-04-21","cited_by_count":36,"area":"agents"},{"id":"2503.08669","title":"SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints","created":"2025-03-11","cited_by_count":23,"area":"agents"},{"id":"2506.08119","title":"SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents","created":"2025-06-09","cited_by_count":23,"area":"agents"},{"id":"2506.03828","title":"AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance","created":"2025-06-04","cited_by_count":15,"area":"agents"},{"id":"2505.11368","title":"GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents","created":"2025-05-16","cited_by_count":14,"area":"agents"},{"id":"2512.20798","title":"A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents","created":"2025-12-23","cited_by_count":13,"area":"agents"},{"id":"2507.14447","title":"Routine: A Structural Planning Framework for LLM Agent System in Enterprise","created":"2025-07-19","cited_by_count":9,"area":"agents"},{"id":"2601.20613","title":"AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios","created":"2026-01-28","cited_by_count":9,"area":"agents"},{"id":"2601.14230","title":"MASCOT: Multi-Agent Socio-Collaborative Companion Systems","created":"2026-01-20","cited_by_count":7,"area":"agents"},{"id":"2606.15367","title":"S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents","created":"2026-06-13","cited_by_count":5,"area":"agents"},{"id":"2608.11727","title":"Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents","created":"2026-08-12","cited_by_count":4,"area":"agents"},{"id":"2606.09118","title":"ComplexConstraints and Beyond: Expert Rubrics for RLVR","created":"2026-06-08","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":"2506.02357","title":"Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2506.04255","title":"HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization","created":"2025-06-01","cited_by_count":2,"area":"agents"},{"id":"2508.09125","title":"LogicIF: Towards Complex Logic Instruction Following","created":"2025-08-12","cited_by_count":2,"area":"agents"},{"id":"2509.22356","title":"RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation","created":"2025-09-26","cited_by_count":2,"area":"agents"},{"id":"2510.11588","title":"Analyzing and Internalizing Complex Policy Documents for LLM Agents","created":"2025-10-13","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":"2605.05716","title":"More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2507.04889","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","created":"2025-07-07","cited_by_count":0,"area":"agents"},{"id":"2605.09283","title":"A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web","created":"2026-05-10","cited_by_count":0,"area":"agents"},{"id":"2605.27784","title":"WIRE: Profiling Witnessed Within-Policy Instruction Collisions in LLM Agents","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2609.05224","title":"First Things First: Teaching LLM-Based Agents to Prioritize Must-Haves before Nice-to-Haves","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.09458","title":"ContractEval: Query-Conditioned Execution Matching for Procedural Instruction Conformance","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.14992","title":"MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2610.15481","title":"SkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.16859","title":"ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}