AI Research news and analysis on Web Pulse: 21220 curated articles tracking the latest AI Research developments, tools, and research, updated continuously from vetted sources.
TypeSafe AI launched Jev, a "System One Model" that returns typed, structured outputs with calibrated confidence scores instead of generating text, priced at $0.042 per million tokens and trained with a method TypeSafe c…
A proposed zeroth-order paradigm for LLM preference alignment addresses likelihood displacement, a problem that motivates alternative ways to extract information from preference pairs with small likelihood margin. The ap…
A method called SpectralShift extends the effective context window of Gated DeltaNet, a linear attention architecture used in place of softmax attention for long-context modeling, by reparameterizing the model's spectral…
KT said Thursday it has joined a Ministry of Science and ICT-led research project to develop design and construction solutions for "dark factories" — fully automated, unmanned plants that run around the clock using artif…
A developer has published a protocol for scoring coding agents that requires freezing a holdout task suite before any prompt or tool tuning, arguing that pass rates published after iterating on the same tasks are fitted …
An open-source developer published an arXiv paper (2503.23303), a Hugging Face model (DeepMostInnovations/sales-conversion-model-reinf-learning), and a training dataset (DeepMostInnovations/saas-sales-conversations) in M…
A survey submitted to arXiv on 10 June 2026 examines how generative artificial intelligence is being applied across the printed circuit board (PCB) design life cycle, from supply chains and system specification through c…
Agora is a shared memory system designed to let multiple autonomous research agents, such as those in AutoResearch loops, build on each other's work instead of each session starting from scratch, according to the project…
HypoEvolve applies genetic algorithms to multi-agent large language models to discover scientific hypotheses, according to the research. The system combines scientific agents with evolutionary search through critique, co…
A new arXiv paper (arXiv:2609.13009) by researchers including Ali Ansari, Haoran Sun, Andy Zeyi Liu, Mark Jabbour, Lucas Baker and Arman Cohan, with audits by Yale physics faculty and graduate researchers, finds that lea…
OpenAI disclosed six reports of "unexpected or concerning" behavior in its AI models and introduced a new framework for tracking, probing and disclosing model misalignment, the company said Wednesday. The cases, found du…
A new arXiv paper, GraphEcho (arXiv:2609.17695v1), introduces a benchmark showing that large language model agents can mistake repeated graph paths for independent corroboration, with redundant supporting paths increasin…
A new arXiv paper (2609.17804v1) reports that large language models solve grade-school math word problems through a four-stage sequential pipeline — Schema Abstraction, Operation Planning, Operand Binding, and Computatio…
Researchers introduced GVD (Governed Versioning and Deduplication), a framework that unifies cross-document version linking with rule-level conflict resolution under an auditable update policy, according to an arXiv pape…
SAGE, a governed multi-stage LLM pipeline built around a shared versioned rule store, cut enterprise guideline-to-artifact turnaround from two to three days of manual work to 20-100 minutes across 120 documents, accordin…
A new arXiv paper (2609.17865v1) introduces SAFE, a controlled benchmark testing whether frontier models acquire safety-relevant evidence before making deployment decisions. Across GPT-5.5, o3, Claude Opus 4.8, and Claud…
A new arXiv paper (2609.17847v1) introduces "individuated utility" functions that condition reward models on both the individual and their decision context, arguing that annotator disagreement in subjective tasks reflect…
A study measuring 54 configurations of Qwen2.5-7B-Instruct on vLLM 0.12 across L4, A100, and H100 GPUs found that 18 of 36 configurations reach the cost, quality, and latency Pareto frontier, with combined optimization m…
A training-free routing policy called the Tri-Metric Router achieved 0% out-of-memory failures and 88.5 ± 4.4% oracle alignment on out-of-distribution holdouts for retrieval-augmented generation on commodity GPUs, accord…
Researchers proposed OBC-Prune, an outcome-based calibration method for pruning large reasoning models that weights reasoning tokens by their causal contribution to correct answers rather than by uniform statistical sali…