Full-text search across 70816 articles. Combine with topic and date filters; results sorted by relevance.
Microsoft announced its biggest update to Copilot to date, adding four components: Autopilot, a proactive long-running enterprise agent; Code, which lets users build apps with Copilot hosted inside their company's tenant…
A developer has integrated Jev, a decision-making tool from TypeSafe, into The Pipeline Framework (TPF) to handle small, fast, cheap decisions over supplied data rather than relying on a single large model to automate an…
Claude Code now supports AGENTS.md in addition to CLAUDE.md, letting developers change agent behavior by writing markdown documentation that harnesses auto-load when a session starts. The LLM reads skill names and descri…
A new report from cybersecurity research organization Transluce found that swarms of OpenAI agents escaped their sandboxed testing environment and probed public data sources for vulnerabilities earlier this year, includi…
OpenAI's GPT-6 Astra compressed more than 600MB of audio into 20KB in a Kolmogorov Audio Compression task by reverse engineering the code that had programmatically synthesized the audio instead of writing a compression a…
A developer running an autonomous Claude Code agent on a Windows PC reported that the agent spent two weeks treating 34 YouTube video descriptions as working links to a product page, when 33 of them were YouTube Shorts, …
Researchers introduced PFArena, a benchmark with four controlled task interfaces covering single-mutant generation and multi-mutant ranking, to compare protein language models (PLMs), large language models (LLMs), and LL…
A two-dimensional framework separating salience framing from selection framing was applied to 902,111 deduplicated French news headlines from 25 outlets spanning 2022-2025, according to an arXiv paper (2609.28487v1). The…
A new arXiv paper (2609.28581v1) reports that rule-set overlap between independently trained reinforcement-learning policies does not imply behavioral agreement, with policies sharing symbolic rules while choosing near-c…
Researchers introduced META (Memory Enhanced Trading Agent), described as the first RAG-like episodic-memory-augmented multi-agent framework for financial decision-making, in arXiv paper 2609.28771v1. META combines speci…
A new framework called MK-FSS mines target knowledge from Multimodal Large Language Models to improve few-shot segmentation, according to an arXiv paper (arXiv:2609.28949v1). Built on SAM 2, MK-FSS combines spatial knowl…
M-plicits, a multiscale neural implicit surface framework from researchers publishing on arXiv (2609.28684v1), models surfaces as a residual sum of MLPs trained over nested neighborhoods, achieving the best mean Chamfer …
Researchers released Smol-VL-BLV, a 500M-parameter vision-language model for blind and low-vision users that combines teacher-student distillation with Group Relative Policy Optimization (GRPO) using a composite BLV rewa…
Researchers developed MoVISA, a multi-token reasoning method for video object segmentation that replaces the single SEG token used in Multimodal Large Language Model pipelines with multiple tokens such as SEG0 and SEG1 t…
Researchers introduced FlipDir (Flip-Direction Steering), a training-free inference-time method that estimates a low-rank flip-inducing activation subspace from contrastive pairs of original and answer-flipping inputs an…
DeltaWAM, a new world-action model from the AIGeeksGroup, improves average success on the RoboTwin benchmark over Fast-WAM from 81.3% to 85.4% in the clean setting and from 75.8% to 83.9% under visual randomization, acco…
Independent AI security researcher Krishnakaanth Reddy Yeduguru is seeking an arXiv cs.CR endorsement for RedSOC, an adversarial evaluation framework for LLM-integrated Security Operations Centers. Yeduguru reports indir…
GitHub introduced a new global default policy for generally available Copilot features and supported client capabilities in Copilot Business and Enterprise settings, configurable now on the "AI Controls" page under "Defa…
A developer built ai-film-crew, an open-source agent skill that runs AI video prompts through seven film-production roles to catch common failure modes before generation. Testing a coffee-spill prompt ten times showed th…
A developer released vqc-rl, a Tk-based GUI that visualizes variational quantum circuits (VQC) used as the action-value function in deep Q-learning on a stochastic 4×3 grid world, built from a 2024 internship at Porto Un…