Reducing LLM costs by 30% with validation-aware, multi-tier caching The post Zero-Waste Agentic RAG: Designing Caching Architectures to Minimize Latency and LLM Costs at Scale appeared first on Towards Data Science.

Ver mais

Amazon Research Awards issues fall 2025 call for proposals The submission opens October 1 and closes on November 12, 2025 October 01, 12:26 PM October 29, 03:31 PM As the Amazon Research Awards (ARA) program continues to expand in scope, so does our call for proposals list. To that end, starting October 1, we will open the fall 2025 call for proposals in eight research areas listed below. AI for Information Security AWS Agentic AI Automated Reasoning Build […]

Ver mais

arXiv:2601.18858v1 Announce Type: new Abstract: Compositional generalization-the ability to interpret novel combinations of familiar components-remains a persistent challenge for neural networks. Behavioral evaluations reveal when models fail but offer limited insight into why failures arise at the representational level. We introduce Homomorphism Error (HE), a structural metric that quantifies deviations from approximate homomorphisms between the expression algebra and a model’s hidden-state space. We instantiate HE for two compositional operators in SCAN-style tasks: modifier HE for unary composition and […]

Ver mais

Ashforth and Anand show how bad acts become business as usual—first embedded in routines, then justified by clever self-deception, and finally taught to newcomers as “how we do things.” The villain isn’t a monster in the mirror, but a system that slowly teaches good people to forget what good means.

Ver mais

arXiv:2602.20366v1 Announce Type: new Abstract: In recent work, it has been shown that maintaining reliability in analog vector–matrix multipliers can be modeled as the following coding problem. Vectors in $mathbb{R}^k$ are encoded into codewords of a linear $[n,k,d]$ code $C$ over $mathbb{R}$. For prescribed positive reals $delta < Delta$, additive errors of magnitude at most $delta$ are tolerable and need no handling, yet outlying errors of magnitude greater than $Delta$ are to be located or detected. The trade-off […]

Ver mais

arXiv:2603.00202v1 Announce Type: new Abstract: We study the expected star discrepancy under a newly designed class of non-equal volume partitions. The main contributions are twofold. First, we establish a strong partition principle for the star discrepancy, showing that our newly designed non-equal volume partitions yield stratified sampling point sets with lower expected star discrepancy than classical jittered sampling. Specifically, we prove that $mathbb{E}(D^{*}_{N}(Z)) < mathbb{E}(D^{*}_{N}(Y))$, where $Y$ and $Z$ represent jittered sampling and our non-equal volume partition sampling, […]

Ver mais

arXiv:2602.15112v1 Announce Type: new Abstract: We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper’s repository, we preserve the datasets, evaluation harness, and baseline implementations but withhold the paper’s proposed method. This results in five containerized task environments comprising 39 sub-tasks in total. Within each environment, agents must propose novel hypotheses, run experiments, and attempt […]

Ver mais

arXiv:2602.05172v1 Announce Type: new Abstract: We derive finite-particle rates for the regularized Stein variational gradient descent (R-SVGD) algorithm introduced by He et al. (2024) that corrects the constant-order bias of the SVGD by applying a resolvent-type preconditioner to the kernelized Wasserstein gradient. For the resulting interacting $N$-particle system, we establish explicit non-asymptotic bounds for time-averaged (annealed) empirical measures, illustrating convergence in the emph{true} (non-kernelized) Fisher information and, under a $mathrm{W}_1mathrm{I}$ condition on the target, corresponding $mathrm{W}_1$ convergence for […]

Ver mais

Scientific discovery pipelines typically involve complex, rigid, and time-consuming processes, from data preparation to analyzing and interpreting findings. Recent advances in AI have the potential to transform such pipelines in a way that domain experts can focus on interpreting and understanding findings, rather than debugging rigid pipelines or manually annotating data. As part of an active collaboration between data science/AI researchers and behavioral neuroscientists, we showcase an example AI-enhanced pipeline, specifically designed to transform and accelerate the way […]

Ver mais