Skip to content

Author

Jia-Peng Li

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents

LIMBO, a deterministic sandbox of six services with realistic contracts and twelve fault modes injected at the service boundary and twelve fault modes injected at the service boundary, is introduced, proving that no verification-only policy is exactly-once under late commits without a bound on in-flight time.

Jia-Peng Li · 1 citation
#machine learning Preprint Sep 2026

Counterfactual Tool Ranking under Utility, Cost, and Privilege Constraints

Counterfactual tool evaluation must distinguish authority, historical support, and what a comparison actually estimates. We study these distinctions with eleven executable enterprise-inspired tools, exact-propensity logs, and real local Model Context Protocol transport. An initial 45-run synthetic study is retained, th...

Jia-Peng Li · 3 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.