{"list":"other","total":61,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2304.08244","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","created":"2023-04-14","cited_by_count":591},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2303.13408","title":"Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense","created":"2023-03-23","cited_by_count":429},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"id":"2310.12823","title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","created":"2023-10-19","cited_by_count":338},{"id":"2412.21139","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","created":"2024-12-30","cited_by_count":336},{"id":"2504.21798","title":"SWE-smith: Scaling Data for Software Engineering Agents","created":"2025-04-30","cited_by_count":285},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"1905.12457","title":"A backdoor attack against LSTM-based text classification systems","created":"2019-05-29","cited_by_count":227},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222},{"id":"2403.02502","title":"Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents","created":"2024-03-04","cited_by_count":197},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166},{"id":"2305.15060","title":"Who Wrote this Code? Watermarking for Code Generation","created":"2023-05-24","cited_by_count":141},{"id":"2009.03015","title":"Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding","created":"2020-09-07","cited_by_count":130},{"id":"2410.10989","title":"Liger Kernel: Efficient Triton Kernels for LLM Training","created":"2024-10-14","cited_by_count":130},{"id":"2412.09605","title":"AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials","created":"2024-12-12","cited_by_count":130},{"id":"2306.17194","title":"On the Exploitability of Instruction Tuning","created":"2023-06-28","cited_by_count":116},{"id":"2210.00875","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","created":"2022-09-27","cited_by_count":86},{"id":"2310.12362","title":"REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models","created":"2023-10-18","cited_by_count":78},{"id":"2506.21506","title":"Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge","created":"2025-06-26","cited_by_count":76},{"id":"2510.07192","title":"Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples","created":"2025-10-08","cited_by_count":72},{"id":"2002.00937","title":"Radioactive data: tracing through training","created":"2020-02-03","cited_by_count":67},{"id":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58},{"id":"2402.16187","title":"No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices","created":"2024-02-25","cited_by_count":50},{"id":"2110.12925","title":"CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning","created":"2021-10-25","cited_by_count":47},{"id":"2402.10892","title":"Proving membership in LLM pretraining data via data watermarks","created":"2024-02-16","cited_by_count":40},{"id":"2303.11470","title":"Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking","created":"2023-03-20","cited_by_count":37},{"id":"2308.14401","title":"CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models","created":"2023-08-28","cited_by_count":34},{"id":"2411.05451","title":"WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models","created":"2024-11-08","cited_by_count":30},{"id":"2404.14461","title":"Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs","created":"2024-04-22","cited_by_count":28},{"id":"2210.04688","title":"BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets","created":"2022-10-07","cited_by_count":25},{"id":"2411.05277","title":"Revisiting the Robustness of Watermarking to Paraphrasing Attacks","created":"2024-11-08","cited_by_count":25},{"id":"2306.08350","title":"Multi-target Backdoor Attacks for Code Pre-trained Models","created":"2023-06-14","cited_by_count":23},{"id":"2505.05190","title":"Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks","created":"2025-05-08","cited_by_count":18},{"id":"2507.09108","title":"SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation","created":"2025-07-12","cited_by_count":12},{"id":"2406.14841","title":"TabularMark: Watermarking Tabular Datasets for Machine Learning","created":"2024-06-21","cited_by_count":8},{"id":"2509.07287","title":"Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm","created":"2025-09-08","cited_by_count":5},{"id":"2504.07002","title":"DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction","created":"2025-04-09","cited_by_count":4},{"id":"2005.00323","title":"Designing Robust API Monitoring Solutions","created":"2020-05-01","cited_by_count":2},{"id":"2506.13494","title":"Watermarking LLM-Generated Datasets in Downstream Tasks","created":"2025-06-16","cited_by_count":1},{"id":"2512.07342","title":"PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning","created":"2025-12-08","cited_by_count":1}],"next_cursor":null}