ICFP/SPLASH 2025 (series) / LMPL 2025 (series) / LMPL 2025 /
Programming Large Language Models with Algebraic Effect Handlers and the Selection Monad
This program is tentative and subject to change.
Wed 15 Oct 2025 17:00 - 17:15 at Orchid Small - Neuro-Symbolic Language/Agent Design Chair(s): Yang Feng
We present Pangolin, a programming language that treats large language model (LLM) interactions as first-class algebraic effects, enabling systematic composition and control over complex AI systems. By modeling non-deterministic choices of LLM results with selection monads, Pangolin allows programmers to abstract over multiple execution paths and automatically select outcomes based on downstream metrics. Pangolin makes it possible to design and manage LLM-centric pipelines with the clarity and reliability of conventional programming languages.
This program is tentative and subject to change.
Wed 15 OctDisplayed time zone: Perth change
Wed 15 Oct
Displayed time zone: Perth change
16:00 - 17:40 | |||
16:00 15mTalk | Vibe Coding Needs Vibe Reasoning – Improving Vibe Coding with Formal Verification LMPL | ||
16:15 15mTalk | Current Practices for Building LLM-Powered Reasoning Tools Are Ad Hoc—and We Can Do Better LMPL Aaron Bembenek The University of Melbourne Pre-print | ||
16:30 15mTalk | Composable Effect Handling for Programming LLM-integrated Scripts LMPL Di Wang Peking University Pre-print | ||
16:45 15mTalk | The LLM Era Demands Natural-Language-Aligned Theorem Provers for Mathematics LMPL Qinxiang Cao Shanghai Jiao Tong University, Lihan Xie Shanghai Jiao Tong University, Junchi Yan Shanghai Jiao Tong University | ||
17:00 15mTalk | Programming Large Language Models with Algebraic Effect Handlers and the Selection Monad LMPL Shangyin Tan University of California, Berkeley, Guannan Wei Tufts University, Koushik Sen University of California at Berkeley, Matei Zaharia UC Berkeley | ||