{"total":34,"rows":[{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75,"area":"agents"},{"id":"2503.07919","title":"BEARCUBS: A benchmark for computer-using web agents","created":"2025-03-10","cited_by_count":31,"area":"agents"},{"id":"2504.05862","title":"Are Generative AI Agents Effective Personalized Financial Advisors?","created":"2025-04-08","cited_by_count":18,"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":"2601.12910","title":"SciCoQA: Quality Assurance for Scientific Paper--Code Alignment","created":"2026-01-19","cited_by_count":10,"area":"agents"},{"id":"2504.16939","title":"A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions","created":"2025-04-07","cited_by_count":9,"area":"agents"},{"id":"2605.28721","title":"LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?","created":"2026-05-27","cited_by_count":5,"area":"agents"},{"id":"2510.07414","title":"Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation","created":"2025-10-08","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":"2601.10702","title":"Grounding Agent Memory in Contextual Intent","created":"2026-01-15","cited_by_count":4,"area":"agents"},{"id":"2606.15385","title":"Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds","created":"2026-06-13","cited_by_count":4,"area":"agents"},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2608.30724","title":"BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks","created":"2026-08-31","cited_by_count":4,"area":"agents"},{"id":"2606.07379","title":"Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests","created":"2026-06-05","cited_by_count":3,"area":"agents"},{"id":"2604.10480","title":"Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs","created":"2026-04-12","cited_by_count":2,"area":"agents"},{"id":"2610.02267","title":"Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses","created":"2026-10-01","cited_by_count":2,"area":"agents"},{"id":"2604.21255","title":"When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors","created":"2026-04-23","cited_by_count":1,"area":"agents"},{"id":"2609.00070","title":"AutoXRD: Autonomous LLM Agents and Comprehensive Evaluation for Powder Diffraction Analysis","created":"2026-08-30","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2604.06013","title":"Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis","created":"2026-04-07","cited_by_count":0,"area":"agents"},{"id":"2605.18918","title":"ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection Defense","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2605.24699","title":"MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional","created":"2026-05-23","cited_by_count":0,"area":"agents"},{"id":"2606.27397","title":"SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2606.27595","title":"Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2607.02141","title":"A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2608.03154","title":"ANCHOR-RE: An Agentic Neuro-Symbolic Framework for Grounded Biomedical Relation Extraction","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.09988","title":"OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents","created":"2026-08-06","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":"2609.19524","title":"A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.22592","title":"AutoGym: Blueprint-First Generation of Verifiable Agent Gyms","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.33691","title":"When Do Agents Help? Embedding, LLM and Agentic Alignment of Classical Texts and Their Translations","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.36161","title":"From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36739","title":"Frontier Autolab: Organizational Memory, Adversarial Dissent and Temporal Leakage in Multi-Agent LLM Firms Across Fifty Years of Technological Change","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.04168","title":"Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"}],"next_cursor":null}