Tag
A technical deep-dive blog post on how dynamically typed language runtimes replace hash-table-based attribute storage with object shapes/maps (hidden classes) to speed up attribute reads and writes, building toward a small, comprehensible implementation inspired by CF Bolz-Tereick's 'A Simple Object Model'.
Maxwell is a new model that dynamically rewrites the binaries of running AI programs like Whisper and LTX-2 at runtime to speed them up, using formal verification to confirm the optimized version preserves correctness.
This survey examines efficient GUI agents through a systems lens, focusing on observation, memory, action, and runtime optimization, and identifies key recurring ideas like selective reading and hybrid runtimes.
The article discusses the challenges of managing active context in long-running AI agent workflows, focusing on balancing context retention with efficiency and cost, and seeks practical solutions from the community.
RAMPART is a compile-time memory model and in-RAM block registry for LLM-based agents that uses five composable primitives to manage context assembly with priority-aware ordering and eviction. Experiments across multiple 7-14B models show that block grouping, relevance gating, and schema eviction significantly improve task success rates and reduce prompt token costs.
This paper proposes using language models as selective surrogates to optimize GPU kernel runtime, demonstrating a novel approach to performance forecasting.
SkillSmith is a boundary-first compiler-runtime framework that extracts fine-grained operational boundaries from LLM agent skills, enabling agents to dynamically access only relevant components, reducing solve-stage token usage by 57.44% and thinking iterations by 42.99% on the SkillsBench benchmark.