Autopoiesis uses LLM-driven program synthesis to evolve serving policies online during deployment, delivering up to 53% and average 34% gains over prior LLM serving systems under runtime dynamics.
Theory of linear and integer programming
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Decision-focused training creates linear surrogates for MILPs that include original constraints and accurately predict optimal solutions, outperforming neural network proxies in case studies.
citing papers explorer
-
Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics
Autopoiesis uses LLM-driven program synthesis to evolve serving policies online during deployment, delivering up to 53% and average 34% gains over prior LLM serving systems under runtime dynamics.
-
Decision-Focused Surrogate Modeling for Mixed-Integer Linear Optimization
Decision-focused training creates linear surrogates for MILPs that include original constraints and accurately predict optimal solutions, outperforming neural network proxies in case studies.