{"list":"other","total":51,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2412.14161","title":"TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks","created":"2024-12-18","cited_by_count":326},{"id":"1906.02694","title":"Deep Semi-Supervised Anomaly Detection","created":"2019-06-06","cited_by_count":291},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270},{"id":"2406.19314","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","created":"2024-06-27","cited_by_count":262},{"id":"2406.15927","title":"Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs","created":"2024-06-22","cited_by_count":259},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2206.09426","title":"ADBench: Anomaly Detection Benchmark","created":"2022-06-19","cited_by_count":232},{"id":"1901.01588","title":"PyOD: A Python Toolbox for Scalable Outlier Detection","created":"2019-01-06","cited_by_count":222},{"id":"2005.02359","title":"Classification-Based Anomaly Detection for General Data","created":"2020-05-05","cited_by_count":211},{"id":"2308.08493","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","created":"2023-08-16","cited_by_count":177},{"id":"1911.08623","title":"Deep Anomaly Detection with Deviation Networks","created":"2019-11-19","cited_by_count":153},{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152},{"id":"2311.09783","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models","created":"2023-11-16","cited_by_count":138},{"id":"2402.11208","title":"Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents","created":"2024-02-17","cited_by_count":137},{"id":"2305.17066","title":"Mindstorms in Natural Language-Based Societies of Mind","created":"2023-05-26","cited_by_count":107},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106},{"id":"2406.00799","title":"Get my drift? Catching LLM Task Drift with Activation Deltas","created":"2024-06-02","cited_by_count":72},{"id":"2502.11127","title":"G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems","created":"2025-02-16","cited_by_count":59},{"id":"2306.12251","title":"GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection","created":"2023-06-21","cited_by_count":58},{"id":"2306.00006","title":"Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection","created":"2023-05-29","cited_by_count":43},{"id":"2508.08127","title":"BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks","created":"2025-08-11","cited_by_count":38},{"id":"2507.16488","title":"ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs","created":"2025-07-22","cited_by_count":32},{"id":"2406.14644","title":"Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation","created":"2024-06-20","cited_by_count":30},{"id":"2402.11887","title":"Generative Semi-supervised Graph Anomaly Detection","created":"2024-02-19","cited_by_count":22},{"id":"2402.04513","title":"Online Cascade Learning for Efficient Inference over Streams","created":"2024-02-07","cited_by_count":20},{"id":"2406.03075","title":"Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework","created":"2024-06-05","cited_by_count":19},{"id":"2406.15523","title":"Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark","created":"2024-06-21","cited_by_count":18},{"id":"2006.03689","title":"Anomaly Detection with Domain Adaptation","created":"2020-06-05","cited_by_count":13},{"id":"2503.12505","title":"MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification","created":"2025-03-16","cited_by_count":13},{"id":"2312.14329","title":"Invariant Anomaly Detection under Distribution Shifts: A Causal Perspective","created":"2023-12-21","cited_by_count":8},{"id":"2503.10042","title":"EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability","created":"2025-03-13","cited_by_count":6},{"id":"2504.00446","title":"Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics","created":"2025-04-01","cited_by_count":6},{"id":"2506.03964","title":"Causality-Aware Contrastive Learning for Robust Multivariate Time-Series Anomaly Detection","created":"2025-06-04","cited_by_count":6},{"id":"2603.24579","title":"MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination","created":"2026-03-25","cited_by_count":5},{"id":"2607.06807","title":"When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems","created":"2026-07-07","cited_by_count":1}],"next_cursor":null}