{"list":"other","total":104,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"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":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"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":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830},{"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":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2410.10813","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","created":"2024-10-14","cited_by_count":707},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421},{"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":"2306.05301","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","created":"2023-06-08","cited_by_count":393},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2104.05938","title":"QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization","created":"2021-04-13","cited_by_count":365},{"id":"2403.07718","title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","created":"2024-03-12","cited_by_count":363},{"id":"2409.04109","title":"Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers","created":"2024-09-06","cited_by_count":363},{"id":"2412.21139","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","created":"2024-12-30","cited_by_count":336},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327},{"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":"2408.04682","title":"ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities","created":"2024-08-08","cited_by_count":295},{"id":"1802.08802","title":"Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration","created":"2018-02-24","cited_by_count":284},{"id":"2107.07567","title":"Beyond Goldfish Memory: Long-Term Open-Domain Conversation","created":"2021-07-15","cited_by_count":267},{"id":"2409.08264","title":"Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale","created":"2024-09-12","cited_by_count":223},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2310.16049","title":"MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning","created":"2023-10-24","cited_by_count":201},{"id":"2406.18518","title":"APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets","created":"2024-06-26","cited_by_count":198},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","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":"2502.14143","title":"Multi-Agent Risks from Advanced AI","created":"2025-02-19","cited_by_count":163},{"id":"2412.05467","title":"The BrowserGym Ecosystem for Web Agent Research","created":"2024-12-06","cited_by_count":161},{"id":"2407.15711","title":"AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?","created":"2024-07-22","cited_by_count":158},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157},{"id":"2205.00445","title":"MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning","created":"2022-05-01","cited_by_count":156},{"id":"2407.10362","title":"LAB-Bench: Measuring Capabilities of Language Models for Biology Research","created":"2024-07-14","cited_by_count":156},{"id":"2402.09727","title":"A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts","created":"2024-02-15","cited_by_count":146},{"id":"2306.06624","title":"RestGPT: Connecting Large Language Models with Real-World RESTful APIs","created":"2023-06-11","cited_by_count":135},{"id":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133},{"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":"2406.04520","title":"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning","created":"2024-06-06","cited_by_count":128},{"id":"2409.11363","title":"CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark","created":"2024-09-17","cited_by_count":123},{"id":"2009.11423","title":"Task-Oriented Dialogue as Dataflow Synthesis","created":"2020-09-24","cited_by_count":122},{"id":"2406.12373","title":"WebCanvas: Benchmarking Web Agents in Online Environments","created":"2024-06-18","cited_by_count":121},{"id":"2502.12115","title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","created":"2025-02-17","cited_by_count":105},{"id":"2503.04957","title":"SafeArena: Evaluating the Safety of Autonomous Web Agents","created":"2025-03-06","cited_by_count":102},{"id":"2406.06769","title":"DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents","created":"2024-06-10","cited_by_count":100},{"id":"2410.06992","title":"SWE-Bench+: Enhanced Coding Benchmark for LLMs","created":"2024-10-09","cited_by_count":99},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91},{"id":"2407.05291","title":"WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks","created":"2024-07-07","cited_by_count":90},{"id":"2104.06486","title":"MS2: Multi-Document Summarization of Medical Studies","created":"2021-04-13","cited_by_count":80},{"id":"2405.08355","title":"Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark","created":"2024-05-14","cited_by_count":63},{"id":"2404.09992","title":"MMInA: Benchmarking Multihop Multimodal Internet Agents","created":"2024-04-15","cited_by_count":55},{"id":"2501.10132","title":"ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario","created":"2025-01-17","cited_by_count":55},{"id":"2409.07440","title":"SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories","created":"2024-09-11","cited_by_count":52},{"id":"2502.05352","title":"ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks","created":"2025-02-07","cited_by_count":51},{"id":"2409.03797","title":"NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls","created":"2024-09-04","cited_by_count":48},{"id":"2406.07835","title":"SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature","created":"2024-06-10","cited_by_count":41},{"id":"2402.15491","title":"API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs","created":"2024-02-23","cited_by_count":39},{"id":"2409.14908","title":"KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems","created":"2024-09-23","cited_by_count":39},{"id":"2410.05669","title":"ACPBench: Reasoning about Action, Change, and Planning","created":"2024-10-08","cited_by_count":39},{"id":"2408.14354","title":"SWE-bench-java: A GitHub Issue Resolving Benchmark for Java","created":"2024-08-26","cited_by_count":34},{"id":"2412.02883","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","created":"2024-12-03","cited_by_count":34},{"id":"2312.06853","title":"LLF-Bench: Benchmark for Interactive Learning from Language Feedback","created":"2023-12-11","cited_by_count":33},{"id":"2405.20477","title":"Automated Focused Feedback Generation for Scientific Writing Assistance","created":"2024-05-30","cited_by_count":33},{"id":"2410.22394","title":"AAAR-1.0: Assessing AI's Potential to Assist Research","created":"2024-10-29","cited_by_count":24}],"next_cursor":"100"}