Research map / Large language models / AI and society
SysMoBench: Evaluating AI on Formally Specifying Complex Real-World Systems
Qian Cheng, Ruize Tang, Emilie Ma, Finn Hackett, Peiyang He, Yiming Su, Ivan Beschastnikh, Yu Huang, Xiaoxing Ma, Tianyin Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use code translation agent instead of basic modeling agent (ablation) | Claude-Sonnet-4 · Etcd Raft | invariant correctness: 69.23% -> 92.31% | Improved |
| use code translation agent instead of basic modeling agent (ablation) | Claude-Sonnet-4 · Etcd Raft | runtime correctness: 25.00% -> 66.67% | Improved |
| use code translation agent instead of basic modeling agent (ablation) | Claude-Sonnet-4 · Etcd Raft | conformance: 7.69% -> 15.38% | Improved |
| use code translation agent instead of basic modeling agent (ablation) | GPT-5 · Etcd Raft | syntax correctness: 47.87% -> 100.00% | Improved |
| use code translation agent instead of basic modeling agent (ablation) | DeepSeek-R1 · Etcd Raft | syntax correctness: 50.00% -> 100.00% | Improved |
| use code translation agent instead of basic modeling agent (ablation) | Gemini-2.5-Pro · Etcd Raft | syntax correctness: 50.00% -> 44.44% | Hurt |
| use code translation agent instead of basic modeling agent (ablation) | GPT-5 · Asterinas Spinlock | invariant correctness: 100.00% -> 85.71% | Hurt |
| swap system from Spinlock to Etcd Raft (larger system) | basic modeling agent, GPT-5 · Etcd Raft vs Spinlock | syntax correctness: 100.00% -> 47.87% | Hurt |
| temporal liveness invariants vs safety invariants | LLM-generated models · SysMoBench invariants | violation rate: 8.3% safety violated vs 41.9% liveness violated | Hurt |
| replace TLA+ with Alloy or PAT | basic modeling agent · Asterinas Spinlock | syntax correctness: TLA+ 100.00% -> Alloy 0.00% (Claude-Sonnet-4) | Hurt |
Closest papers by meaning
- Verify0: Can AI Agents Build Formally Verified Software Repositories? (NeurIPS 2026 · similarity 0.86)
- Commit0: Library Generation from Scratch (ICLR 2025 · similarity 0.85)
- ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox (ICML 2026 · similarity 0.84)
- AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions (ICML 2026 · similarity 0.84)
- Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain (ICLR 2024 · similarity 0.84)
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces (ICLR 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
