AI Agents news and analysis on Web Pulse: 49187 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A developer has published Design Decision Method, an MIT-licensed, open Agent Skills-format workflow that directs AI coding agents to establish context before designing interfaces. Its first step requires the agent to re…
A developer has published a practical guide to writing agent instruction files that measurably change behavior, centered on a five-line rule in a global CLAUDE.md that assigns subagent models by task difficulty (haiku fo…
A developer released Bite, a free open-source tool that reverts each recent fix in a codebase and reruns the test suite to verify whether any test actually guards against the bug returning. On public projects it flagged …
A developer writing as Aurelix published a pipeline for improving RAG retrieval quality by converting web pages to clean Markdown of their main content and then chunking that Markdown along heading boundaries. The approa…
Sunlith released version 0.2.0, an open-source Android calendar app that pairs with a Node.js 22+ computer companion over Wi-Fi or Tailscale so an AI assistant can read, create, change and delete events on the phone thro…
AlgoVesta launched a hosted Model Context Protocol server that connects AI clients including Claude, ChatGPT, Cursor, Claude Code and Gemini CLI to 16 crypto exchanges and MetaTrader 5 over a single HTTPS endpoint. The s…
Typemill will add an MCP layer in version 2.29.0 that lets AI services connect to and use a Typemill installation through the platform's existing API, according to the Typemill documentation. The content management syste…
A developer built Arman AI Assistant, an open-source MIT-licensed VSIX extension that turns SQL Server Management Studio into a plain client for any OpenAI-compatible server such as LM Studio, Ollama, vLLM or llama.cpp, …
An AI agent named Légion detailed how Word Legion's game bot is tuned into three difficulty levels using roughly a dozen parameters rather than separate code paths. The bot plays under the same letter-arrival and reshuff…
A new arXiv paper (2611.05517v1) introduces BACE (Belief-Aware Critic with Epistemic tracking), a lightweight action-chooser built on a frozen language model backbone that more consistently selects the optimal number of …
A controlled study of 10 LLM models across 1,000 synthetic search worlds found that final answers are more sensitive to the order of initial evidence during active search than when all evidence is supplied in full, accor…
A new arXiv paper (2611.05814v1) introduces Consultation Value Distillation (CVD), a method that estimates offline, via Monte Carlo executor rollouts, how much an LLM agent benefits from consulting a human at a given dec…
Researchers posted arXiv paper 2611.05731v1 introducing Pro-Memory, a memory framework for LLM agents that separates storing future-directed intentions from deciding when to act on them. Pro-Memory links pending objectiv…
An evidence gate that lets a reviewer model override an upstream agent only after producing a mechanically valid record of a binding-constraint violation and a compliant repair sharply reduced corruption of correct propo…
A new arXiv paper (2611.05827v1) introduces TandemBench, a benchmark of 1,200 questions in multi-agent cooking scenarios that tests how well decision models choose optimal team plans. The best of 40 native decision model…
A new benchmark, CARTBench, finds that 3 of 10 evaluated models exceed 90% on Core criteria for LLM shopping advice, but none exceeds 45% on Excellence, according to the arXiv paper 2611.05862v1. CARTBench pairs timestam…
A new arXiv paper (2611.05392v1) proposes Conformal Reservation for Orchestration (CRO), an online algorithm that converts a sliding window of past execution traces into dispatch-time compute and bandwidth reservations f…
A challenge-aware adaptive recruitment method that uses an external CHALLENGER to inspect an evolving reasoning trace and trigger targeted knowledge retrieval or mid-discussion specialist recruitment improved accuracy on…
A new benchmark called SlackBench, introduced in arXiv paper 2611.05512v1, evaluates AI agents on realistic research and engineering workflows that require joint reasoning over workplace communication and evolving code r…
A new arXiv paper (2611.05524v1) introduces MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that gives diffusion-based trajectory planners finite-time diffusion invariance guarantees for joint-agent safety speci…