{"total":11,"items":[{"citing_arxiv_id":"2605.18636","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents","primary_cat":"cs.CV","submitted_at":"2026-05-18T16:43:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SPIKE dual-controller framework raises success rates 5-9 points and cuts tokens 55% in StarDojo agents by reusing strategic plans across stable segments and escalating only at detected events.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13918","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CA2: Code-Aware Agent for Automated Game Testing","primary_cat":"cs.SE","submitted_at":"2026-05-13T12:52:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CA2 integrates call stack information into RL agents for game testing and shows consistent gains over baselines that ignore code signals.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09965","ref_index":137,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","primary_cat":"cs.CV","submitted_at":"2026-05-11T04:16:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper organizes research on generalist game AI into Dataset, Model, Harness, and Benchmark pillars and charts a five-level progression from single-game mastery to agents that create and live inside game multiverses.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"RL self-evolution in a multi-game environment, showing that perception and reasoning mutually bootstrap during training. CoSo [40] improves exploration efficiency by using counterfactual reasoning to focus RL updates on action-critical tokens. Game-RL [153] synthesizes verifiable reasoning data from game source code and applies GRPO-based training [137], finding that RL on game data alone transfers to broader vision- language benchmarks. VL-DAC [14] decouples token-level PPO [135] updates from environment-step value estimation, demonstrating that RL training in lightweight simulators generalizes to real-image agentic control. Collectively, these efforts confirm that RL post-training consistently sharpens VLM decision-making in game"},{"citing_arxiv_id":"2605.10990","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries","primary_cat":"cs.SE","submitted_at":"2026-05-09T11:41:53+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round repair success from 10% to 78%.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[21] Bertrand Meyer. Applying'design by contract'.Computer, 25(10):40-51, 2002. [22] Joon Sung Park, Joseph O'Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. Generative agents: Interactive simulacra of human behavior. InProceed- ings of the 36th annual acm symposium on user interface software and technology, pages 1-22, 2023. [23] Maria Abi Raad, Arun Ahuja, Catarina Barros, Frederic Besse, Andrew Bolt, Adrian Bolton, Bethanie Brownfield, Gavin Buttimore, Max Cant, Sarah Chakera, et al. Scaling instructable agents across many simulated worlds.arXiv preprint arXiv:2404.10179, 2024. [24] Melika Sepidband, Hamed Taherkhani, Hung Viet Pham, and Hadi Hemmati. Rgfl: Reasoning guided fault localization for automated program repair using large language models."},{"citing_arxiv_id":"2605.00347","ref_index":41,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-05-01T02:05:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Odysseus adapts PPO with a turn-level critic and leverages pretrained VLM action priors to train agents achieving at least 3x average game progress over frontier models in long-horizon Super Mario Land.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20987","ref_index":21,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks","primary_cat":"cs.AI","submitted_at":"2026-04-22T18:17:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"COSPLAY co-evolves an LLM decision agent with a skill bank agent to improve long-horizon game performance, reporting over 25.1% average reward gains versus frontier LLM baselines on single-player benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08340","ref_index":69,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models","primary_cat":"cs.CV","submitted_at":"2026-04-09T15:12:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"PokeGym is a new benchmark that tests VLMs on long-horizon tasks in a complex 3D game using only visual observations, identifying deadlock recovery as the primary failure mode.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[68] Harsh Trivedi, Tushar Khot, Mareike Hartmann, Ruskin Manku, Vinty Dong, Edward Li, Shashank Gupta, Ashish Sabharwal, and Niranjan Balasubramanian. 2024. Appworld: A controllable world of apps and people for benchmarking interactive coding agents. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 16022-16076. [69] Xinyu Wang, Bohan Zhuang, and Qi Wu. 2025. Are large vision language models good game players?arXiv preprint arXiv:2503.02358(2025). [70] Zihao Wang, Shaofei Cai, Anji Liu, Yonggang Jin, Jinbing Hou, Bowei Zhang, Haowei Lin, Zhaofeng He, Zilong Zheng, Yaodong Yang, et al. 2024. Jarvis-1: Open-world multi-task agents with memory-augmented multimodal language"},{"citing_arxiv_id":"2601.11218","ref_index":54,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Video Game Accessibility through Shared Control for People with Upper-Limb Impairments","primary_cat":"cs.HC","submitted_at":"2026-01-16T11:49:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A configurable framework called GamePals enables shared control via human cooperation or partial automation to improve video game accessibility for people with upper-limb impairments, evaluated in a study with 13 participants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.02544","ref_index":52,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","primary_cat":"cs.AI","submitted_at":"2025-09-02T17:44:45+00:00","verdict":"CONDITIONAL","verdict_confidence":"UNKNOWN","novelty_score":5.0,"formal_verification":"none","one_line_summary":"UI-TARS-2 reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld while attaining 59.8 mean normalized score on a 15-game suite through multi-turn RL and scalable data generation.","context_count":1,"top_context_role":"baseline","top_context_polarity":"baseline","context_text":"high throughput, making it possible to run millions of interactive rollouts reliably. Empirical evaluation shows that UI-TARS-2 delivers significant improvements over UI-TARS-1.5 [56], achieving strong results in both GUI-based interaction and game environments. On GUI benchmarks, the model reaches 88.2 on Online-Mind2Web [77], 47.5 on OSWorld [75], 50.6 on WindowsAgentArena [10], and 73.3 on AndroidWorld [52], representing clear gains over the previous generation and outperforming strong baselines such as Claude and OpenAI agents in multiple cases. In game environments, UI-TARS-2 attains a mean normalized score of 59.8 across a 15-game suite-roughly 60% of human-level performance-and surpasses strong baselines such as OpenAI CUA and Claude Computer Use by factors of 2."},{"citing_arxiv_id":"2509.02132","ref_index":54,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Shared Control for Game Accessibility: Understanding Current Human Cooperation Practices to Inform the Design of Partial Automation Solutions","primary_cat":"cs.HC","submitted_at":"2025-09-02T09:29:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Interviews with 14 accessible gamers identify essential shared-control practices, key limitations of human assistance, and design requirements for software agents that could automate support.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.20414","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RetroMotion: Retrocausal Motion Forecasting Models are Instructable","primary_cat":"cs.CV","submitted_at":"2025-05-26T18:05:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Retrocausal transformer decomposes multi-agent motion forecasts into marginals and pairwise joints, models uncertainty with compressed exponentials, achieves strong Waymo results, generalizes to Argoverse 2 and V2X-Seq, and enables implicit instruction following from standard training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}