{"total":19,"rows":[{"id":"2411.11581","title":"OASIS: Open Agent Social Interaction Simulations with One Million Agents","created":"2024-11-18","cited_by_count":132,"area":null},{"id":"2505.17826","title":"Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models","created":"2025-05-23","cited_by_count":19,"area":null},{"id":"2504.21582","title":"MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework","created":"2025-04-30","cited_by_count":12,"area":null},{"id":"2606.12344","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks","created":"2026-06-10","cited_by_count":8,"area":null},{"id":"2505.10887","title":"InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction","created":"2025-05-16","cited_by_count":7,"area":null},{"id":"2503.03258","title":"Exploring the Potential of Large Language Models as Predictors in Dynamic Text-Attributed Graphs","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2604.08963","title":"Aligned Agents, Biased Swarm: Measuring Bias Amplification in Multi-Agent Systems","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.18418","title":"MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.22446","title":"From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.13213","title":"Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.01316","title":"Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2601.03137","title":"Accurate Table Question Answering with Accessible LLMs","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2603.11333","title":"LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2605.13172","title":"When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2608.27992","title":"GOD: Govern, Observe, and Direct - A Real-Time Control Room for Agent Societies","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.00759","title":"Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.20095","title":"A Scalable Trust Discovery Architecture for the Internet of Agents","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.26927","title":"Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.27871","title":"Bounded Loops: Pre-Run Spend Bounds, Proved Termination, and Verified Completion for Agent Harnesses","created":"2026-08-20","cited_by_count":0,"area":null}],"next_cursor":null}