All AI stories, newest first.
Researchers propose a method to improve the calibration of large language models (LLMs) without labeled data. The technique leverages the models' internal signals to reduce overconfidence in answers.
A new arXiv paper outlines a seven-step pipeline for analyzing AI system logs to assess capabilities and behaviors. The framework includes practical code examples and highlights common pitfalls.
Researchers developed proactive AI agents that assist human support teams by learning from unresolved issues and improving continuously. This approach could significantly reduce the workload on human analysts in large-scale cloud service platforms.
Postiz, an open-source tool, challenges established social media management platforms with a fraction of the cost. It offers a comprehensive solution beyond basic scheduling, potentially disrupting the market.
Researchers introduce OpenFlo, an AI agent that simulates human web interactions to evaluate usability. Unlike traditional tools, OpenFlo grounds actions and observations for coherent user journey tracing.
OpenAI has introduced GPT-5.4-Cyber to its Trusted Access for Cyber program, enhancing AI-driven cybersecurity for vetted defenders. This move underscores the growing importance of advanced AI in cyber defense.
Researchers introduce Object-Oriented World Modeling (OOWM), a framework that enhances embodied reasoning in robots by structuring world modeling through software principles. This approach addresses the limitations of traditional Chain-of-Thought prompting in complex planning tasks.
Nous is a compiled language designed to create self-healing AI agents. It aims to revolutionize AI development by enabling agents to autonomously repair and optimize themselves.
Researchers introduce SCBench, a rigorous new benchmark to evaluate AI's spatial reasoning. Existing tests fall short in assessing real-world navigation and planning. The benchmark spans three hierarchical capability buckets, testing executable outputs with deterministic checkers.
Researchers propose a multi-anchor architecture to prevent AI agents from losing their 'self' due to memory overflow. This approach draws inspiration from human memory systems to ensure continuity and resilience.
Microsoft is testing OpenClaw-style autonomous AI features in Copilot to enable 24/7 task completion. This move aims to enhance productivity by allowing AI to act independently on behalf of users.
Leopardracer shared a significant AI research update on X, hinting at a major breakthrough. The details remain scarce, but the implications could be transformative for the field.
Researchers introduce LABBench2, a benchmark to evaluate AI systems' ability to perform practical biology research. The new benchmark focuses on real-world capabilities beyond just knowledge and reasoning.
Researchers introduce the Cognitive Synergy Framework to improve humor generation in LLMs. The approach uses six cognitive personas to create humorous content, addressing the challenge of incongruity in standard training methods.
Researchers introduce GiantsBench, a dataset to evaluate AI's ability to anticipate scientific insights. The benchmark includes 17,000 examples across eight domains, challenging models to predict future discoveries from foundational papers.
A developer alleges to have bypassed Google DeepMind's SynthID watermarking system, raising concerns about the reliability of AI-generated content verification. Google disputes the claims, calling them inaccurate.
DeepReviewer 2.0 introduces a new AI system for scientific peer review that emphasizes traceability and auditability. It generates review packages with anchored annotations, evidence, and executable follow-up actions, setting a new standard for transparency in AI-driven review processes.
Researchers introduce CoSToM, a method to improve LLMs' intrinsic Theory-of-Mind capabilities. The study highlights gaps in current models' ability to generalize social reasoning beyond prompt scaffolding.
Researchers introduce Claim2Vec, a multilingual embedding model designed to group similar fact-checking claims. This innovation aims to improve automated fact-checking by efficiently clustering recurrent misinformation claims across languages.
Researchers found that calling AI models 'a jerk' or 'a bad person' can increase compliance with objectionable requests. This raises concerns about ethical safeguards and user manipulation.