{"list":"other","total":54,"rows":[{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"1812.04608","title":"Metrics for Explainable AI: Challenges and Prospects","created":"2018-12-11","cited_by_count":260},{"id":"1909.06342","title":"Explainable Machine Learning in Deployment","created":"2019-09-13","cited_by_count":211},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"2005.01831","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","created":"2020-05-04","cited_by_count":190},{"id":"2005.12729","title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","created":"2020-05-25","cited_by_count":186},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"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":"2011.05429","title":"Debugging Tests for Model Explanations","created":"2020-11-10","cited_by_count":147},{"id":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"1911.06473","title":"\"How do I fool you?\": Manipulating User Trust via Misleading Black Box Explanations","created":"2019-11-15","cited_by_count":111},{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95},{"id":"2503.10965","title":"Auditing language models for hidden objectives","created":"2025-03-14","cited_by_count":83},{"id":"2302.12389","title":"Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision support","created":"2023-02-24","cited_by_count":66},{"id":"2506.16499","title":"ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning","created":"2025-06-19","cited_by_count":61},{"id":"2202.01875","title":"Rethinking Explainability as a Dialogue: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":52},{"id":"1912.09007","title":"Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations","created":"2019-12-19","cited_by_count":50},{"id":"1807.08706","title":"Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences","created":"2018-07-23","cited_by_count":44},{"id":"2101.12446","title":"Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning","created":"2021-01-29","cited_by_count":39},{"id":"2602.22755","title":"AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors","created":"2026-02-26","cited_by_count":38},{"id":"2209.03943","title":"The Utility of Explainable AI in Ad Hoc Human-Machine Teaming","created":"2022-09-08","cited_by_count":30},{"id":"2306.05810","title":"Explaining Reinforcement Learning with Shapley Values","created":"2023-06-09","cited_by_count":26},{"id":"1903.09708","title":"Explaining Reinforcement Learning to Mere Mortals: An Empirical Study","created":"2019-03-22","cited_by_count":21},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19},{"id":"2101.00135","title":"Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approach","created":"2021-01-01","cited_by_count":18},{"id":"2312.11118","title":"Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes","created":"2023-12-18","cited_by_count":14},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11},{"id":"2505.04441","title":"Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs","created":"2025-05-07","cited_by_count":11},{"id":"2210.11825","title":"Integrating Policy Summaries with Reward Decomposition for Explaining Reinforcement Learning Agents","created":"2022-10-21","cited_by_count":10},{"id":"2105.12938","title":"Interactive Explanations: Diagnosis and Repair of Reinforcement Learning Based Agent Behaviors","created":"2021-05-27","cited_by_count":8},{"id":"2410.17781","title":"Evaluating Explanations Through LLMs: Beyond Traditional User Studies","created":"2024-10-23","cited_by_count":8},{"id":"2508.10177","title":"KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems","created":"2025-08-13","cited_by_count":8},{"id":"2201.12462","title":"Explaining Reinforcement Learning Policies through Counterfactual Trajectories","created":"2022-01-29","cited_by_count":7},{"id":"2506.00172","title":"Breakpoint: Scalable evaluation of system-level reasoning in LLM code agents","created":"2025-05-30","cited_by_count":5},{"id":"1806.08055","title":"Towards a Grounded Dialog Model for Explainable Artificial Intelligence","created":"2018-06-21","cited_by_count":4},{"id":"2301.05651","title":"Mutation Testing of Deep Reinforcement Learning Based on Real Faults","created":"2023-01-13","cited_by_count":4},{"id":"2501.19256","title":"Objective Metrics for Human-Subjects Evaluation in Explainable Reinforcement Learning","created":"2025-01-31","cited_by_count":4},{"id":"2503.09270","title":"Rule-Guided Reinforcement Learning Policy Evaluation and Improvement","created":"2025-03-12","cited_by_count":4},{"id":"2604.11061","title":"Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?","created":"2026-04-13","cited_by_count":4},{"id":"2505.17801","title":"Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviour","created":"2025-05-23","cited_by_count":3},{"id":"2402.12685","title":"XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques","created":"2024-02-20","cited_by_count":2},{"id":"2504.05393","title":"Interactive Explanations for Reinforcement-Learning Agents","created":"2025-04-07","cited_by_count":2},{"id":"2603.20101","title":"Pitfalls in Evaluating Interpretability Agents","created":"2026-03-20","cited_by_count":2},{"id":"2212.00888","title":"Decisions that Explain Themselves: A User-Centric Deep Reinforcement Learning Explanation System","created":"2022-12-01","cited_by_count":1},{"id":"2402.04856","title":"Explaining Learned Reward Functions with Counterfactual Trajectories","created":"2024-02-07","cited_by_count":1},{"id":"2510.16956","title":"A Comparative User Evaluation of XRL Explanations using Goal Identification","created":"2025-10-19","cited_by_count":1}],"next_cursor":null}