{"total":23,"rows":[{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2504.13359","title":"Cost-of-Pass: An Economic Framework for Evaluating Language Models","created":"2025-04-17","cited_by_count":35,"area":null},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2510.02453","title":"How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models","created":"2025-10-02","cited_by_count":24,"area":null},{"id":"2506.00582","title":"Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs","created":"2025-05-31","cited_by_count":19,"area":null},{"id":"2505.17968","title":"Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems","created":"2025-05-23","cited_by_count":14,"area":null},{"id":"2503.22402","title":"EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing","created":"2025-03-28","cited_by_count":13,"area":null},{"id":"2503.10242","title":"MinorBench: A hand-built benchmark for content-based risks for children","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2506.06376","title":"Enhancing Decision-Making of Large Language Models via Actor-Critic","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2509.06337","title":"Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2605.13414","title":"TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints","created":"2026-05-13","cited_by_count":6,"area":null},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2601.19001","title":"FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2504.04877","title":"System Log Parsing with Large Language Models: A Review","created":"2025-04-07","cited_by_count":3,"area":null},{"id":"2505.20182","title":"An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2508.02094","title":"\"Harmless to You, Hurtful to Me!\": Investigating the Detection of Toxic Languages Grounded in the Perspective of Youth","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2606.23537","title":"SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2510.02660","title":"When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2605.02411","title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.02661","title":"AcademiClaw: When Students Set Challenges for AI Agents","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2609.25299","title":"Making Agents More Consistent: Skills Should Form Habits for Repeat Tasks","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.38486","title":"Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigations","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.05697","title":"From Token-Max to Outcome-Max: How You Use AI Determines Its Productivity","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}