SpeedrunBench is a new benchmark that tests large language model agents on their ability to develop and refine strategies for completing nine different video games as quickly as possible. The benchmark requires agents to repeatedly improve, reflect, and reason over long action horizons to beat both themselves and other players. Experiments show that while agents can approach human records on simple platformers, they lag behind humans on longer, more complex games within realistic resource limits.
By Yoshinari Fujinuma, Keisuke Kamahori, Ryuto Koike, Abdelrahman Madkour, Varun Prashant Gangal, Monty Bichouna, Martyna Markiewicz, Shivani Jain, Duncan Curtis, Rebecca Qian, Anand Kannappan
Learn2Play Bench is a new benchmark that tests how well large language model agents learn from experience in unfamiliar, text‑based games with novel or counterintuitive rules. The benchmark provides reproducible feedback, automatic scoring, and varied game instances to evaluate learning across repeated attempts and transfer to new situations. Findings show that retaining full action records aids learning, human players outperform agents, and the choice of harness significantly impacts performance and inference cost.
By Yibo Li, Jinhang Qiu, Zhi Zheng, Qianyun Guo, Jiaying Wu, Shuo Ji, Bryan Hooi
arXiv:2609.38881v1 Announce Type: new
Abstract: Real-time strategy (RTS) games require agents to coordinate economic development, production and construction, base defense, unit organization, and att...
By Xinhe Tian, Xiaoyue Zhang, Ziyou Zhang, Jiacheng Li, Xiaoqiang Jin, Qianchuan Zhao, Gaochen Cui
arXiv:2607. 02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see.
By Xiangchen Cheng, Yunwei Jiang, Jianwen Sun, Zizhen Li, Chuanhao Li, Xiangcheng Cao, Yihao Liu, Fanrui Zhang, Li Jin, Kaipeng Zhang
The paper explores a runtime strategy-selection framework where a large language model (LLM) guides a pre‑trained reinforcement learning (RL) policy for non‑player characters (NPCs) in a Unity combat game without altering the underlying policy. Five NPC agents sharing a PPO policy were compared in a baseline setup and an LLM‑augmented setup, where a locally hosted Mistral 7B model assigns one of four tactical tags every five seconds based on live game state. Across 600 episodes against three scripted opponents, the LLM‑augmented agents more than doubled their win rate against a Balanced opponent, improved performance against an Evasive opponent, but struggled against an Aggressive opponent due to over‑reliance on encirclement; analysis of 2,430 strategy selections revealed limited zero‑shot differentiation with the model favoring Surround in 83.8% of cases.
By Hrithika Deepu Nair, Kayvan Karim
arXiv:2608. 12626v1 Announce Type: cross Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals.
By Yi Wu, Zhimin Hu
PTCG-Bench is a new benchmark that uses the Pokémon Trading Card Game to evaluate large language model (LLM) agents on two fronts: their decision‑making within a single complex game environment and their capacity to evolve through accumulated experience. The benchmark includes a modular harness ablation to isolate agent performance from model capability. Experiments show that while LLM agents can achieve non‑trivial gameplay, sustained self‑evolution remains difficult and performance depends on harness design.
By Dongdong Hua, Yifei Sun, Renhong Huang, Feng Gao, Chunping Wang, Yang Yang
arXiv:2607. 29577v1 Announce Type: new Abstract: Games and simulators make valuable benchmarks by turning decisions into measurable outcomes, but many current suites under-test rules-rich tactical reasoning: the ability to choose well when geometry, timing, resources, objectives, and rule interactions all matter at once.
By Ismayil Ismayilov, Atakan Kara, Kaan Oktay
arXiv:2610.14883v1 Announce Type: new
Abstract: We present MARL-BattleGrounds (MARL-BGs), an easy-to-use JAX-native benchmark for heterogeneous and competitive multi-agent reinforcement learning (MAR...
By Ulixes Tariq Hawili, Subramanian Ramamoorthy, Yoann Altmann, Ignacio Carlucho
M-Plan is a closed‑loop multi‑agent system that combines long‑term and short‑term memory to improve large language model agents on long‑horizon, multi‑turn tasks. It uses task‑specific milestones and local hints to generate global‑local guidance, forming short‑term memory during execution, and then optimizes and stores relevant information in long‑term memory for future use. Experiments on ALFWorld, Webshop, and PDDL show that M‑Plan outperforms baseline methods in both accuracy and efficiency.
By Ziyang Liu, Jiakang Yuan, Jiayuan Fan, Tao Chen
arXiv:2606. 01993v1 Announce Type: cross Abstract: Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks.
By Xinyu Che, Junqi Xiong, Yunfei Ge, Xinping Lei, Shihao Li, Hang Yan, Han Li, Yuanxing Zhang, Zhiqi Bai, Jinhua Hao, Ming Sun, Han Li, Jiaheng Liu
UnifiedPlayers is a cooperative framework that jointly adapts planning, execution, and evaluation for tool-integrated reinforcement learning agents. It consists of a Planning Player that generates tasks, an Execution Player that creates multi-turn trajectories with Python tool calls, and an Evaluation Player that builds executable verifiers, all coordinated by role‑specific rewards under GRPO. The approach outperforms prior baselines on mathematical and general reasoning benchmarks and yields a verifier with high adversarial detection accuracy and more discriminative reward signals.
By Wenjie Liao, Liangjie Zhao, Zehong Cao