Latest in AI and developer tools

Today's trail

updated 27m ago

Last hour Today

Pulse · techzine.eu

techzine.eu · Oct 27

Neural Concept wants AI agents to do engineering grunt work

Pulse · fintech.global

fintech.global · Oct 27

Fortinet wants to secure agents before they go awol with inline AI security service

Backbase, an Amsterdam-based provider of banking software, has launched Delivery Factory, an AI-powered platform designed to accelerate software development by pairing banking delivery teams with specialist AI agents throughout the development lifecycle. The company said teams using the platform across more than 10 implementations over the past year completed work at twice the pace of […]

Pulse

Top picks this weekarXiv

arXiv

Oct 26

Retriever-Free Retrieval: Navigating Documents with Decision Models

While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query.

Top picks

All arXiv Hugging Face GitHub Hacker News

Latest Top this week

arXiv

Sep 20

Optimal No-Regret Learning for Repeated Prophet Inequality

We study repeated prophet inequalities under prefix feedback. In each of $T$ rounds, a learner encounters fresh values drawn independently from $n$ boxes with unknown $[0,1]$-supported distributions in a fixed order and must irrevocably accept one, observing only the prefix up…

arXiv

Sep 20

Judging a Review by its Cover: A Reliability Analysis of LLM-based Peer Review Evaluation Metrics

Peer-review evaluation is increasingly being automated with LLM-as-a-judge metrics, but this creates a measurement risk. A review may receive a high score because it is fluent, organized, and polished, rather than because it provides a strong evaluation of the paper. This risk…

arXiv

Sep 20

Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning

Subliminal Learning (SL) is a recently identified phenomenon in which a student model acquires downstream task capabilities by matching seemingly unrelated auxiliary outputs from a teacher, despite never observing task labels, task-specific outputs, or the original training…

arXiv

Sep 20

CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learning

Time series forecasting underpins critical decision-making across diverse domains. While large language models (LLMs) offer promising reasoning capabilities, existing LLM-based time series forecasting approaches either reduce them to numerical predictors that bypass their…

This week in Multimodal

This week

Get the morning digest

Today's trail

Pulse

Top picks

Today's trail

This week in Multimodal

Most active this week

Rising tools