{"total":37,"rows":[{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130,"area":null},{"id":"2505.15146","title":"lmgame-Bench: How Good are LLMs at Playing Games?","created":"2025-05-21","cited_by_count":55,"area":null},{"id":"2512.00193","title":"A Rosetta Stone for AI Benchmarks","created":"2025-11-28","cited_by_count":36,"area":null},{"id":"2602.17594","title":"AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games","created":"2026-02-19","cited_by_count":12,"area":null},{"id":"2510.18560","title":"WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality","created":"2025-10-21","cited_by_count":11,"area":null},{"id":"2604.06543","title":"The Illusion of Stochasticity in LLMs","created":"2026-04-08","cited_by_count":9,"area":null},{"id":"2412.06438","title":"Can foundation models actively gather information in interactive environments to test hypotheses?","created":"2024-12-09","cited_by_count":8,"area":null},{"id":"2503.09617","title":"Factorio Learning Environment","created":"2025-03-06","cited_by_count":7,"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":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2505.16334","title":"Panoptic Captioning: An Equivalence Bridge for Image and Text","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2505.17010","title":"Understanding Prompt Tuning and In-Context Learning via Meta-Learning","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2607.01224","title":"AutoMem: Automated Learning of Memory as a Cognitive Skill","created":"2026-07-01","cited_by_count":5,"area":null},{"id":"2509.01328","title":"Can Large Language Models Master Complex Card Games?","created":"2025-09-01","cited_by_count":4,"area":null},{"id":"2605.09965","title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2608.12593","title":"DiG-bench: Discovery in Games","created":"2026-08-12","cited_by_count":3,"area":null},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2602.17497","title":"Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2502.11733","title":"Plant in Cupboard, Orange on Rably, Inat Aphone. Benchmarking Incremental Learning of Situation and Language Model using a Text-Simulated Situated Environment","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2509.00074","title":"Language and Experience: A Computational Model of Social Learning in Complex Tasks","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.26298","title":"Can Agent Conquer Web? Exploring the Frontiers of ChatGPT Atlas Agent in Web Games","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2602.16902","title":"LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.08340","title":"Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2606.28514","title":"GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2509.19924","title":"Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2602.10009","title":"Discovering High Level Patterns from Simulation Traces","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.02348","title":"Same Pieces, Different Servers: A Tetris Benchmark for AI Agents as Served","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2606.05896","title":"Resonant Minds: Closed-Loop Social Avatars with Theory of Mind","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2608.05148","title":"Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.11018","title":"Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.16189","title":"Position: AI Is Not Ready for Strategic Conflicts","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.22308","title":"GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language Agents","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.25001","title":"GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.14807","title":"ASIWorld: Benchmarking Autonomous Agents in a Persistent Survival Sandbox","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.18579","title":"Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}