context: proactive agents via sandboxed programs
context replaces reactive chatbots with proactive agents that advance tasks without user prompts using precomputed context, sandboxed programs, and goal-driven state machines.
aitag research
summaries filed under research
optimizing latency, reliability, and cost in llm agent workflows
a study models tradeoffs in llm-based agent workflows and proposes a water-filling token allocation policy to balance speed, accuracy, and expense.
aipope leo xiv's ai encyclical highlights human dignity
the vatican's new encyclical on artificial intelligence offers clear ethical guidance on interpretability, bias, accountability, and environmental impact.
ailatent cache flow sends model thoughts without text
a new method lets ai models share compressed internal states directly, skipping slow text generation and handling different contexts.
aisciatlas: a 157m-entity knowledge graph for science
sciatlas builds a massive knowledge graph from 43 million papers to help ai navigate scientific literature with structured reasoning.
aineurosymbolic framework translates natural language to temporal logic
a new architecture combines neural translation with formal verification to produce correct linear temporal logic from natural language.
aifusionsense: adaptive near-sensor learning for multimodal edge ai
a new framework trains lightweight near-sensor classifiers to decide what data to transmit, reducing energy and latency in multimodal edge systems.
aiagentic system tackles research-level math proofs
rma uses specialized agents to solve open math problems by searching literature, building knowledge, and iteratively refining proofs.
aiwhy centerloss hurts ood detection and multi-scale mahalanobis wins
a new method called goen uses multi-scale features and mahalanobis distance to beat deep ensembles on out-of-distribution detection, while revealing that centerloss harms performance.
aiosctom uses rl to test nested belief conflicts in llms
a new method generates complex theory of mind scenarios where an observer's view of another agent clashes with their own belief, challenging llms with recursive reasoning.
aitool-augmented agent for closed-loop cad-cae optimization
a reinforcement learning framework teaches llms to orchestrate cad generation, cae solving, and geometry revision until constraints are met.
aispecialization beats scale in ai procurement
a 3b specialized model outperformed frontier apis at lower cost, showing training alignment matters more than parameter count.
aitext degeneration costs more than you think
a small fraction of autoregressive model requests can loop into repetition, inflating batch inference time by over 40% and exposing a blind spot in standard benchmarks.
aiadaptive rbf-kan adds dynamic shape parameters to kolmogorov-arnold networks
a new study extends fastkan by using leave-one-out cross-validation to set kernel shape parameters and adding matern and wendland kernels for more flexible function approximation.
ailanguage models learn to forecast research idea success
a new method trains language models to predict which research ideas will work better without running experiments, using a dataset of 11,488 idea pairs from paperswithcode.
aiuniform weak propagation-of-chaos in shallow neural nets
new bounds show how finite-width neural network outputs stay close to their infinite-width mean-field limit over all training time, without needing strong convexity or noise.
aisafer offline policy picks for ad auctions
a new framework helps ad platforms decide which reserve-price policies are worth testing, using logged data without overpromising gains.
ailocal covariate selection without strong assumptions
a new method selects covariates for causal effect estimation without requiring pretreatment or causal sufficiency assumptions, using local learning to avoid global structure search.
aino feature ranking is faithful, stable, and complete under collinearity
a new proof shows that feature rankings cannot be simultaneously faithful, stable, and complete when features are correlated, and proposes an ensemble method as a solution.
aibest small language models on hugging face now
a curated look at top small language models under 7b parameters on hugging face, with benchmarks and code to get started.
ai