Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents
cs.CL
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/floatai/xiangqibench
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- gpt-oss-120b & gpt-oss-20b Model Card
- The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
- Evaluating Large Language Models Trained on Code
- Xiangqi-R1: Enhancing Spatial Strategic Reasoning in LLMs for Chinese Chess via Reinforcement Learning
- GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents
- TextArena
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
- Kimi K2.5: Visual Agentic Intelligence
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering