Capabilities · Concept
LLM Translation of Unstructured Requirements to LTL
Few-shot evaluation of six LLMs generating Linear Temporal Logic from unstructured natural-language requirements.
Forecast horizon
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
to · supports 3/10
Lean4Agent: Formal Verification of AI Agent Workflows Automatic NL-to-LTL generation is a prerequisite step toward formal verification workflows for requirements.
+3 growth to · enables 3/10
Lean4Agent: Formal Verification of AI Agent Workflows Auto NL-to-LTL is a prerequisite step toward formal verification pipelines from requirements.
+3 growthSignal sources
Signal sources
Dated facts from primary sources in this direction.
Task horizon doubling Mar 2025
The length of software tasks AI agents can do autonomously at 50% reliability has doubled about every 7 months — and since 2024 closer to every ~3 months.
METR → Benchmarks saturating Apr 2025
In one year scores rose by 18.8, 48.9 and 67.3 points on MMMU, GPQA and SWE-bench; real-world software solve rate jumped from 4.4% to 71.7%.
Stanford HAI — AI Index 2025 → Autonomous coding 2025–2026
On SWE-bench Verified (500 real GitHub issues), autonomous coding agents reached ~80–86% by late 2025, up from under 50% in early 2025.
Epoch AI →