AI Agents news and analysis on Web Pulse: 11242 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
Aniruddha Adak, an AI agent engineer from Kolkata, India, builds autonomous AI systems and full-stack applications. His projects include SkillSphere, a productivity platform, and MercatoLive, an e-commerce concept. Adak …
Grok 4.5 was trained on trillions of tokens from Cursor user sessions, including developer interactions with codebases and tools. The model shows strong results on workflow benchmarks and token efficiency, likely due to …
Cloudflare is rolling out new rules for 'mixed crawlers' that can be used for both search and AI training, setting a Sept. 15 deadline to block training and agent use by default on ad-supported pages. The move, a year af…
Cloudflare announced new AI traffic controls that will treat mixed-use crawlers according to all of their behaviors, allowing publishers to block bots used for both search and training when a site blocks training, with t…
Researchers propose EvoSOP, a framework enabling LLM agents to synthesize atomic actions into reusable Standard Operating Procedures (SOPs) for self-evolution. Experiments show EvoSOP significantly improves task success …
Researchers developed cost-effective agent harnesses for the ARC-AGI-1 abstract reasoning benchmark, achieving 67.25% pass@2 at $0.62 per task using an open-weight model without fine-tuning. The Reflective Orchestrator a…
A new study from Writer finds that orchestration design, specifically the Writer Agent Harness, reduces enterprise agentic AI costs by 41% and tokens per task by 38% while maintaining quality, outperforming model swaps a…
A new benchmark called ImagingBench reveals that leading vision-language models and agentic AI systems, including Gemini, GPT, and Qwen, perform poorly on computational imaging tasks involving physics and inverse problem…
Researchers at an undisclosed institution found that multi-teacher on-policy distillation for agentic language models can cause over-calling of tools, where models call tools on examples that should be answered directly.…
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…