{"list":"other","total":51,"rows":[{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2602.15763","title":"GLM-5: from Vibe Coding to Agentic Engineering","created":"2026-02-17","cited_by_count":587},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548},{"id":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501},{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437},{"id":"2407.18901","title":"AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents","created":"2024-07-26","cited_by_count":401},{"id":"2412.14470","title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","created":"2024-12-19","cited_by_count":306},{"id":"2408.04682","title":"ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities","created":"2024-08-08","cited_by_count":295},{"id":"2401.10019","title":"R-Judge: Benchmarking Safety Risk Awareness for LLM Agents","created":"2024-01-18","cited_by_count":288},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240},{"id":"2412.05467","title":"The BrowserGym Ecosystem for Web Agent Research","created":"2024-12-06","cited_by_count":161},{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145},{"id":"2410.06703","title":"ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents","created":"2024-10-09","cited_by_count":133},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121},{"id":"2406.08391","title":"Large Language Models Must Be Taught to Know What They Don't Know","created":"2024-06-12","cited_by_count":100},{"id":"2510.20270","title":"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases","created":"2025-10-23","cited_by_count":65},{"id":"2505.08054","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","created":"2025-05-12","cited_by_count":58},{"id":"2407.16221","title":"Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models","created":"2024-07-23","cited_by_count":57},{"id":"2404.10960","title":"Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations","created":"2024-04-16","cited_by_count":54},{"id":"2405.12063","title":"CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models","created":"2024-05-20","cited_by_count":54},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48},{"id":"2409.00557","title":"Learning to Ask: When LLM Agents Meet Unclear Instruction","created":"2024-08-31","cited_by_count":42},{"id":"2412.06676","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","created":"2024-12-09","cited_by_count":26},{"id":"2406.20015","title":"ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models","created":"2024-06-28","cited_by_count":25},{"id":"2409.06097","title":"ClarQ-LLM: A Benchmark for Models Clarifying and Requesting Information in Task-Oriented Dialog","created":"2024-09-09","cited_by_count":24},{"id":"2507.04250","title":"Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning","created":"2025-07-06","cited_by_count":24},{"id":"2509.07315","title":"SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs","created":"2025-09-09","cited_by_count":22},{"id":"2510.15501","title":"DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios","created":"2025-10-17","cited_by_count":19},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18},{"id":"2508.16260","title":"MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use","created":"2025-08-22","cited_by_count":16},{"id":"2512.04864","title":"Are Your Agents Upward Deceivers?","created":"2025-12-04","cited_by_count":16},{"id":"2602.11199","title":"When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification","created":"2026-02-04","cited_by_count":16},{"id":"2512.21120","title":"ClarifyMT-Bench: Benchmarking and Improving Multi-Turn Clarification for Conversational Large Language Models","created":"2025-12-24","cited_by_count":13},{"id":"2512.16310","title":"Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation","created":"2025-12-18","cited_by_count":11},{"id":"2512.04597","title":"When Robots Should Say \"I Don't Know\": Benchmarking Abstention in Embodied Question Answering","created":"2025-12-04","cited_by_count":10},{"id":"2603.01246","title":"Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders","created":"2026-03-01","cited_by_count":10},{"id":"2605.07769","title":"Coding Agents Don't Know When to Act","created":"2026-05-08","cited_by_count":7},{"id":"2508.11222","title":"ORFuzz: Fuzzing the \"Other Side\" of LLM Safety -- Testing Over-Refusal","created":"2025-08-15","cited_by_count":6},{"id":"2509.01476","title":"Do Retrieval Augmented Language Models Know When They Don't Know?","created":"2025-09-01","cited_by_count":5},{"id":"2605.20544","title":"The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents","created":"2026-05-19","cited_by_count":4},{"id":"2510.08158","title":"Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs","created":"2025-10-09","cited_by_count":3},{"id":"2602.15197","title":"OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction","created":"2026-02-16","cited_by_count":3},{"id":"2606.02965","title":"Designing for Doubt: The Case for Informed Abstention in Autonomous Agents","created":"2026-06-01","cited_by_count":3},{"id":"2602.21265","title":"ToolMATH: A Diagnostic Benchmark for Long-Horizon Tool Use under Systematic Tool-Catalog Constraints","created":"2026-02-24","cited_by_count":1}],"next_cursor":null}