{"list":"other","total":58,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"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":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2001.00973","title":"Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing","created":"2020-01-03","cited_by_count":384},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1606.03137","title":"Cooperative Inverse Reinforcement Learning","created":"2016-06-09","cited_by_count":300},{"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":"2312.06942","title":"AI Control: Improving Safety Despite Intentional Subversion","created":"2023-12-12","cited_by_count":229},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","cited_by_count":198},{"id":"2411.15114","title":"RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts","created":"2024-11-22","cited_by_count":175},{"id":"2402.08567","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","created":"2024-02-13","cited_by_count":153},{"id":"2307.11760","title":"Large Language Models Understand and Can be Enhanced by Emotional Stimuli","created":"2023-07-14","cited_by_count":146},{"id":"2312.04724","title":"Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models","created":"2023-12-07","cited_by_count":138},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135},{"id":"2404.08144","title":"LLM Agents can Autonomously Exploit One-day Vulnerabilities","created":"2024-04-11","cited_by_count":128},{"id":"2406.07814","title":"Collective Constitutional AI: Aligning a Language Model with Public Input","created":"2024-06-12","cited_by_count":123},{"id":"2404.16244","title":"The Ethics of Advanced AI Assistants","created":"2024-04-24","cited_by_count":107},{"id":"2306.07899","title":"Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks","created":"2023-06-13","cited_by_count":103},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99},{"id":"2405.06624","title":"Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems","created":"2024-05-10","cited_by_count":96},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79},{"id":"2410.16464","title":"Beyond Browsing: API-Based Web Agents","created":"2024-10-21","cited_by_count":78},{"id":"2206.04737","title":"Outsider Oversight: Designing a Third Party Audit Ecosystem for AI Governance","created":"2022-06-09","cited_by_count":67},{"id":"2404.00806","title":"Algorithmic Collusion by Large Language Models","created":"2024-03-31","cited_by_count":62},{"id":"2403.02817","title":"Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications","created":"2024-03-05","cited_by_count":59},{"id":"2310.02521","title":"Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem","created":"2023-10-04","cited_by_count":52},{"id":"2402.11651","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","created":"2024-02-18","cited_by_count":50},{"id":"2410.11905","title":"A Scalable Communication Protocol for Networks of Large Language Models","created":"2024-10-14","cited_by_count":45},{"id":"2109.05067","title":"The Flaws of Policies Requiring Human Oversight of Government Algorithms","created":"2021-09-10","cited_by_count":44},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32},{"id":"2311.18751","title":"Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web","created":"2023-11-30","cited_by_count":24},{"id":"2404.06921","title":"GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications","created":"2024-04-10","cited_by_count":23},{"id":"1907.04534","title":"The Role of Cooperation in Responsible AI Development","created":"2019-07-10","cited_by_count":21},{"id":"2406.12137","title":"IDs for AI Systems","created":"2024-06-17","cited_by_count":19},{"id":"2408.07892","title":"Personhood credentials: Artificial intelligence and the value of privacy-preserving tools to distinguish who is real online","created":"2024-08-15","cited_by_count":16},{"id":"2307.12108","title":"An Empirical Study & Evaluation of Modern CAPTCHAs","created":"2023-07-22","cited_by_count":13},{"id":"2403.12107","title":"Scenarios for the Transition to AGI","created":"2024-03-17","cited_by_count":13},{"id":"2310.16042","title":"WebWISE: Web Interface Control and Sequential Exploration with Large Language Models","created":"2023-10-24","cited_by_count":11},{"id":"2405.10295","title":"Societal Adaptation to Advanced AI","created":"2024-05-16","cited_by_count":10},{"id":"2104.03366","title":"An Object Detection based Solver for Google's Image reCAPTCHA v2","created":"2021-04-07","cited_by_count":8},{"id":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8},{"id":"2003.11157","title":"AI loyalty: A New Paradigm for Aligning Stakeholder Interests","created":"2020-03-24","cited_by_count":7},{"id":"2311.07815","title":"Cooperative AI via Decentralized Commitment Devices","created":"2023-11-14","cited_by_count":7},{"id":"2403.14443","title":"Language Models Can Reduce Asymmetry in Information Markets","created":"2024-03-21","cited_by_count":5},{"id":"2410.15650","title":"Voice-Enabled AI Agents can Perform Common Scams","created":"2024-10-21","cited_by_count":5},{"id":"2407.12220","title":"Questionable practices in machine learning","created":"2024-07-17","cited_by_count":4},{"id":"2104.04683","title":"A Low-Cost Attack against the hCaptcha System","created":"2021-04-10","cited_by_count":2},{"id":"2401.05239","title":"Failures of public key infrastructure: 53 year survey","created":"2024-01-10","cited_by_count":2},{"id":"2410.12123","title":"Large Language Models, and LLM-Based Agents, Should Be Used to Enhance the Digital Public Sphere","created":"2024-10-15","cited_by_count":1}],"next_cursor":null}