graph-augmented tree search cuts llm costs in agent planning
gats uses a layered world model and ucb1 tree search to eliminate llm calls during inference, achieving 100% success on synthetic tasks.
aisummaries filed under research
gats uses a layered world model and ucb1 tree search to eliminate llm calls during inference, achieving 100% success on synthetic tasks.
aia new study shows that the drift lipschitz constant k determines how well diffusion policies approximate optimal actions and how they behave statistically with finite data.
aia new method explains temporal graph network predictions by tracing how past events shape node memory vectors through backtracking and topological attribution.
aia new framework explains how humans and large language models can strategically undermine trust in scaffolded public assertions, going beyond echo chambers and misinformation.
aia new method separates score matching from policy training to make adaptive experiment design cheaper and more scalable.
aistudy shows how threshold choices in long-tailed chest x-ray models can miss rare-positive patients, especially in subgroups, and how tail-aware methods reduce underdiagnosis.
aia survey maps clinical reasoning levels to ai methods and tests 18 models on a new benchmark.
aia new method uses model predictions to reduce variance in risk estimation while keeping estimates unbiased, and it adaptively selects which test points to label.
aia new spectrum-aware method recursively consolidates low-rank adapters so each task builds on previous ones without overwriting them.
aistandard conformal prediction under-covers rare classes in imbalanced drug discovery data, but a class-conditional fix restores coverage.
aimeta's muse spark 1.1 model now offers an api with better tool calling and computer use, plus a new cli plugin for easy access.
aisensorfm is a large foundation model pre-trained on over a trillion minutes of wearable sensor data from five million people, learning a general representation of human physiology that transfers across 35 health tasks.
aia hardware study checks if a quantum processor can reliably update beliefs across a sequential decision task without corrupting the planner's posterior.
aia new approach to value-of-information analysis when probabilities are not precisely known, using decision-rule-specific values and fixed-measure envelopes on credal sets.
aia single lightweight controller coordinates attention mode, expert selection, and cache bit-width per token to reduce inference cost without losing quality.
aijarred sumner details how he used ai coding agents to rewrite the bun javascript runtime from zig to rust in 11 days, achieving a safe, stable port with minimal user impact.
aia two-stage agent pipeline using an open-weight model without arc-specific fine-tuning achieves competitive abstract reasoning under strict compute limits.
aia study tests large language and vision models for generating 3d mechanical designs from text, using a framework with iterative refinement.
aia new mathematical model uses fiber bundles to detect when machine learning systems discover causal laws instead of interpolating data.
aifiner temporal disaggregation inflates in-sample fit but degrades out-of-sample accuracy due to recursive error compounding.
ai