{"list":"other","total":56,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"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":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"2209.06899","title":"Out of One, Many: Using Language Models to Simulate Human Samples","created":"2022-09-14","cited_by_count":752},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256},{"id":"2402.14762","title":"MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues","created":"2024-02-22","cited_by_count":250},{"id":"2410.05080","title":"ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery","created":"2024-10-07","cited_by_count":235},{"id":"2501.17399","title":"MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs","created":"2025-01-29","cited_by_count":180},{"id":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178},{"id":"1907.06554","title":"Asking Clarifying Questions in Open-Domain Information-Seeking Conversations","created":"2019-07-15","cited_by_count":139},{"id":"2308.13149","title":"SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research","created":"2023-08-25","cited_by_count":115},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87},{"id":"2401.16745","title":"MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models","created":"2024-01-30","cited_by_count":81},{"id":"2410.13788","title":"Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions","created":"2024-10-17","cited_by_count":76},{"id":"1809.01494","title":"Interpretation of Natural Language Rules in Conversational Machine Reading","created":"2018-08-28","cited_by_count":75},{"id":"2402.11451","title":"SciAgent: Tool-augmented Language Models for Scientific Reasoning","created":"2024-02-18","cited_by_count":70},{"id":"2212.07769","title":"CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models","created":"2022-12-15","cited_by_count":69},{"id":"2311.08166","title":"MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge","created":"2023-11-14","cited_by_count":63},{"id":"2503.22674","title":"QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?","created":"2025-03-28","cited_by_count":63},{"id":"2409.00135","title":"HoneyComb: A Flexible LLM-Based Agent System for Materials Science","created":"2024-08-29","cited_by_count":57},{"id":"2404.11972","title":"Aligning Language Models to Explicitly Handle Ambiguity","created":"2024-04-18","cited_by_count":56},{"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":"2510.05444","title":"SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?","created":"2025-10-06","cited_by_count":50},{"id":"2407.21320","title":"MetaOpenFOAM: an LLM-based multi-agent framework for CFD","created":"2024-07-31","cited_by_count":39},{"id":"2006.05986","title":"ClarQ: A large-scale and diverse dataset for Clarification Question Generation","created":"2020-06-10","cited_by_count":31},{"id":"2305.13808","title":"Asking Clarification Questions to Handle Ambiguity in Open-Domain QA","created":"2023-05-23","cited_by_count":26},{"id":"2402.13374","title":"Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems","created":"2024-02-20","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":"2510.18941","title":"ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge","created":"2025-10-21","cited_by_count":24},{"id":"2504.06260","title":"FEABench: Evaluating Language Models on Multiphysics Reasoning Ability","created":"2025-04-08","cited_by_count":22},{"id":"2309.13233","title":"User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue","created":"2023-09-23","cited_by_count":19},{"id":"2504.09602","title":"Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations","created":"2025-04-13","cited_by_count":18},{"id":"2509.23124","title":"Non-Collaborative User Simulators for Tool Agents","created":"2025-09-27","cited_by_count":18},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18},{"id":"2502.01523","title":"CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering","created":"2025-02-03","cited_by_count":15},{"id":"2510.12171","title":"MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science","created":"2025-10-14","cited_by_count":15},{"id":"2507.21389","title":"Teaching Language Models To Gather Information Proactively","created":"2025-07-28","cited_by_count":14},{"id":"2109.05955","title":"Analysing Mixed Initiatives and Search Strategies during Conversational Search","created":"2021-09-13","cited_by_count":13},{"id":"2311.09182","title":"ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models","created":"2023-11-15","cited_by_count":12},{"id":"2505.10852","title":"MatTools: Benchmarking Large Language Models for Materials Science Tools","created":"2025-05-16","cited_by_count":12},{"id":"2603.21011","title":"ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods","created":"2026-01-08","cited_by_count":12},{"id":"2507.20352","title":"RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing","created":"2025-07-27","cited_by_count":10},{"id":"2601.08118","title":"MirrorBench: A Benchmark to Evaluate Conversational User-Proxy Agents for Human-Likeness","created":"2026-01-13","cited_by_count":7}],"next_cursor":null}