Problem
Research questions and friction points this paper is trying to address.
LLM Reasoning
Dynamic State Spaces
Benchmarking
Petri Nets
PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces
🤖 AI Summary
为解决LLM在动态状态空间推理能力的评估问题，本文提出使用Petri网构建的PetriBench基准测试，通过不同难度的任务家族来全面评估模型性能。
📝 Abstract
Characterizing LLM reasoning remains an open challenge, as many existing benchmarks isolate specific reasoning skills, rely on external knowledge, or are costly to extend. We introduce PetriBench, a compact, fully self-contained, and scalable benchmark for evaluating LLM reasoning over dynamic state spaces using Petri nets, a mature formalism for modeling real-world concurrent and distributed systems. PetriBench organizes reasoning into four task families varying by scope and temporal horizon, with Easy, Medium, and Hard levels generated by increasing structural complexity and evaluated against exact ground truth. Across a diverse set of proprietary and open-weight models, accuracy decreases consistently with difficulty, while harder instances expose increasingly distinct task-specific capability profiles. Additional analyses show that test-time compute improves performance but interacts differently with different reasoning tasks, and that procedural generation yields smooth scaling with structural complexity. Together, these results show that PetriBench provides a unified and extensible setting for probing the strengths, limits, and scaling behavior of LLM reasoning.
Innovation
Methods, ideas, or system contributions that make the work stand out.
PetriBench
dynamic state spaces
Petri nets
scalable benchmark
LLM reasoning
🔎 Similar Papers
No similar papers found.
