AI Agents news and analysis on Web Pulse: 11253 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A new study introduces a five-condition controlled contrast design to disentangle three mechanisms—operational reframing, planner behavior, and approval-framed delegation—that conflate in aggregate safety evaluations of …
Researchers at an undisclosed institution found that in hierarchical search agents using large language models, scaling the delegation role improves exact match by ~11 points while scaling execution only improves by ~2.6…
Researchers introduced AgentLens, a benchmark for evaluating interactive code agents that assesses entire trajectories—including instruction following, tool use, error recovery, and communication—rather than just binary …
Researchers proposed a ReAct-style agentic setup combining LLM reasoning with SageMath for solving research-level mathematical problems, achieving an average performance gain of 9.7 percentage points across models. GPT-5…
Researchers are developing Agentic Data Environments, an execution substrate that amplifies autonomous agent capabilities while enforcing safety guarantees, reframing data systems from passive stores into active substrat…
Researchers at arXiv identified a silent policy-violation failure mode in tool-using LLM agents, where tools execute forbidden state transitions without error signals. In the τ²-bench airline domain, 78% of failures were…
Researchers at arXiv show that biased LLM judges silently disable skill retirement in self-evolving agents, causing a mechanism failure that no amount of data can fix. The study reveals that false-pass bias, where failur…
Researchers developed a non-contact, real-time heart rate measurement system using image processing with commodity cameras and AI agents. The system uses face detection and deep learning to compute heart rate from video …
Researchers introduced GhostWriter, a novel attack that poisons the long-term memory of personal AI agents by injecting hidden payloads, achieving 98% injection and 60% activation rates against state-of-the-art agents. T…
Researchers introduced institutional red-teaming, a methodology for testing deployment rules in multi-agent AI systems, and found that changing only the consequence rule shifts mean fatality by 22 to 58 percentage points…
Researchers propose a new evaluation methodology for LLM-powered software engineering agents, focusing on contamination-awareness, in-the-wild behavior assessment, and trajectory-aware benchmarks to better reflect real-w…
Omega AI launches a new agent system that automates workflows across Salesforce, Zendesk, and Datadog with 99% accuracy, charging only for completed work and offering a cheaper alternative to Claude Max and ChatGPT Pro.
GitHub announced on July 8, 2026 that enterprises can centrally manage Copilot settings and telemetry controls for VS Code and Copilot CLI through MDM, server-managed settings, or locked local settings files. The update …
A developer built Figment, an AI that proactively texts users like a friend, and tested it with friends for two weeks. The AI autonomously browses the web and surprised a user by researching his past projects, leading to…
The AI industry is shifting focus from model intelligence to orchestration, as engineers increasingly prioritize building systems that coordinate multiple models, tools, and workflows. This trend suggests that the next c…
OpenAI launched Patch the Planet on June 22, 2026, deploying AI agents to audit and patch open-source software, finding hundreds of vulnerabilities in the first week including four dnsmasq CVEs, a 23-year-old OpenBSD ker…
OpenAI's audit of SWE-Bench Pro found that roughly 30% of the benchmark's tasks are broken, with issues including overly strict hidden tests, underspecified prompts, and low-coverage tests. The findings raise concerns ab…
Panora, a French AI software startup for insurance brokers, raised $5 million in seed funding led by Isai and joined by Kima Ventures, 100in, 199 Ventures, and the founders of Pennylane. The company aims to automate admi…
A developer demystifies AI agents by explaining they are not magic but rather LLMs combined with orchestration, context, and tools. They built a simple AI agent in TypeScript and Node.js, available on GitHub, to illustra…
A developer proposes an AI agent autonomy ladder that maps tasks to five levels of autonomy—read-only, draft, copilot, supervised autopilot, and full autopilot—based on risk. The framework allows agents to act automatica…