The author developed HEXIS, a compiler that maps skill clauses and tool interfaces into states, local instructions, data bindings and explicit transition conditions.
Compiling agent skills into state machines improves task success
HEXIS separates model reasoning from explicit workflow control, reducing missed steps and execution-token use across four benchmarks.
Li presents an incremental compiler that converts written agent skills into extended finite state machines, which track data and execution progress while enforcing transitions between operations.
Why this paper
Independent · Part of Agent Harness Optimization, now 90 papers
In one line
HEXIS compiles agent skills into extended finite state machines, improving success by 16.2 percentage points over Skill + ReAct and reducing execution tokens by 38.4-88.9% with Qwen3.8-27B.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§