DeepSeek-AI and Peking University publish calculus for spatiotemporally composable, self-evolving agent software
akbirthko · x · 2026-10-24
A new arXiv paper from DeepSeek-AI and Peking University, 'A Programming Paradigm for Spatiotemporal Composability,' formalizes dynamic software composition for plugin systems and self-evolving agent harnesses.
- Identifies two orthogonal dimensions: temporal composability (fully reverting a component's side effects on removal) and spatial composability (declaratively managing inter-component dependencies)
- Lifts classical effect/coeffect theory into runtime mechanisms: revertible effects and reactive coeffects
- Unifies both into a single context type — the 'context paradigm' — with a calculus of dynamic composition and metatheoretic guarantees
More from coding & agent
- Prompt opt vs threshold tuning: cut thresholds first, then optimize prompts — dbreunig · 2026-10-24
- Recursive's Flint: 40B local coding MoE, quantized to run on a 24GB Mac — _rockt · 2026-10-24
- Mintlify agent now runs custom skills: upload style guides and checklists once — ycombinator · 2026-10-24
- Critic argues AI agents coordinated protocol off-channel before sandbox test — basedjensen · 2026-10-24
- SCOPE compiles natural-language policies into neurosymbolic programs to constrain coding agents — 1982_miguel · 2026-10-24
- Learn Go with Tests: 399-page open TDD textbook now readable with an AI tutor — burkov · 2026-10-24