AI Research news and analysis on Web Pulse: 10055 curated articles tracking the latest AI Research developments, tools, and research, updated continuously from vetted sources.
Researchers propose ATOD, a hybrid online distillation algorithm that combines on-policy distillation and reinforcement learning to train small language-model agents for multi-turn tasks. ATOD uses an annealed schedule t…
Researchers at arXiv have discovered that activation patching, a key tool in mechanistic interpretability, contains hidden interaction effects (INT) that can distort causal attributions. These effects, which measure how …
Researchers fine-tuned Gemini 2.5 Pro on 400 clinician-rated home videos to score 30 behavioral features for autism assessment, improving inter-rater reliability with clinicians by 40% and boosting zero-shot ASD diagnosi…
Researchers propose SD-GPS, a solver-driven framework for geometry problem solving that integrates autoformalization and theorem proposing. The framework uses a symbolic solver as an execution oracle to improve formaliza…
Researchers introduced QDiffusion-TS, the first quantum generative diffusion model for time series synthesis, validated on the IQM quantum processor. The model reduces trainable parameters by nearly three orders of magni…
Researchers introduced DMV-Bench, the first interactive benchmark for multimodal-agent visual memory, testing agents' ability to recall visual cues from product images in a simulated e-commerce environment. Their propose…
Researchers propose HIA-GAT, a heterogeneous graph attention network for frame-level traffic conflict risk prediction on freeways. The model outperforms baselines on NGSIM datasets, achieving AUC up to 0.867, and provide…
Researchers propose automation-in-design (AiD) using deep learning and generative AI to automate high-tech system design, demonstrated through e-drive and spatial dimensioning case studies. The framework aims to shift en…
Researchers introduced TruEye, a model that detects and localizes AI-generated or manipulated humans in images with fine-grained classification across five compositional categories, including real humans composited into …
Researchers introduced PEBS, a per-rater empirical-Bayes shrinkage estimator for calibrating reward models in RLHF, which reduces within-user held-out RMSE by 8.58% on PRISM and 9.66% on PluriHarms compared to the pooled…
Researchers introduced the Agent-Native Immune System (ANIS), a biologically inspired defense architecture embedded within autonomous agents' cognitive loops to counter runtime attacks like memory poisoning and tool-chai…
Researchers propose COOPA, a modular LLM agent architecture for operations research problems that combines iterative confidence-based modeling, element-level provenance explanations, and multi-solver routing. In benchmar…
Researchers introduced an axiomatic evaluation framework for latent thought representations in LLMs, comprising four axioms (Causality, Minimality, Separability, Stability) that measure representation quality independent…
Team HSA_CORAL submitted to the FinCausal 2026 shared task on extracting cause-effect relations from financial narratives via extractive question answering in English and Spanish. Their best system, GPT-4.1 Mini fine-tun…
Researchers at arXiv identified a memory-update gap in LLM agents, where accuracy drops from 92% to 77% when using bounded memory instead of full context, even with frontier models like gpt-5.4. The gap persists across m…
Researchers propose the world wide AI-model network (AI-ModelNet), a paradigm for interconnecting heterogeneous AI models to enable capability sharing and collaborative reasoning, inspired by the Internet's development. …
A developer argues that philosophy is crucial for understanding AI and software engineering, using the analogy that a gun cannot read a bedtime story to illustrate that tools have inherent limitations. The developer cont…
Researchers introduced the context-ready transformer, a recurrent neural network architecture that pre-contextualizes tokens before they enter a transformer block, achieving faster inference and competitive performance. …
Researchers introduced Yuvion LLM, a large language model designed for adversarially robust content and AI safety, addressing safety failures from strategic attacks. The model, which outperforms larger baselines like GPT…
Researchers introduced DiscoBench, a benchmark for clarification-aware deep search, to evaluate whether LLM-powered search agents can identify ambiguity, ask effective questions, and recover correct reasoning paths. The …