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 paper posted to arXiv as 2611.07048v1 develops a theoretical framework comparing Darwinian, Lamarckian, and agent-directed evolution in AI, finding that when learning is sufficiently effective the three mechanisms adap…
Researchers posting arXiv paper 2611.07066v1 introduced EFXPLORER, a constrained exploration framework for cooperative multi-agent reinforcement learning that maximizes exploration objectives subject to a constraint pres…
A cross-agent formalization protocol in which a Specifier model translates clinical trial criteria into Dafny predicates and an Implementer model writes methods checked against them reached only 59.3% agreement even in a…
A paper posted to arXiv (2611.07247v1) formalizes a chain of inequalities linking information-theoretic empowerment to capability-based individual power in Markov games, showing that a Fano's inequality-derived floor B(s…
A new arXiv paper (2611.07372v1) introduces EnvOpt, a method for automated end-to-end optimization of stationary agent environments using real or synthetic tasks without graders or reference answers. On AutomationBench, …
A November 2026 arXiv paper (2611.07508v1) proposes DelegateEval, a platform-level evaluation framework for "personal external service agents" — AI agents authorized and continuously managed by an individual to accept cl…
Vis2State, a training-free agentic framework introduced in arXiv paper 2611.07397v1, abstracts visual puzzles into explicit, revisable problem states that link visual inspection and program execution, and achieves state-…
Researchers posted arXiv paper 2611.07408v1 introducing PSGAgent, an agentic framework that lets multimodal large language models dynamically refine visual perception for panoptic scene graph generation through a think-a…
Researchers introduced TB-MathModel, a terminal-style benchmark that makes 18 real CUMCM and MCM contest problems from 2023–2025 agentic and verifiable, scoring agents' single JSON artifacts against reproductions of Outs…
Researchers introduced Agent-R$^2$, a real-source data synthesis framework that distills 4,000 task instances from 10,000 web-corpus candidates to train agents on realistic productivity work, according to the arXiv paper…
A new arXiv paper (2608.11676v2) proposes XBRIDGE, a decode-free communication protocol that lets heterogeneous multi-agent LLM systems share information across different model families without losing entity identity. Th…
Anthropic has introduced message threads for its Messages API, an opt-in change that lets clients send only new messages plus a reference to the prior response instead of resending full conversation history. Anthropic re…
The ThingBoot project published a guide showing how to connect a stock ESP32 to a self-hosted Mosquitto MQTT broker in about 15 minutes, using either the ThingBoot ESP Arduino SDK or plain Arduino with PubSubClient. The …
Howseen founder Raphaël Aubry detailed a production MCP server at app.howseen.ai/api/mcp (version 1.3.0) that exposes the company's AI-visibility data to Claude, ChatGPT and Cursor through 44 tools, 26 of them read-only.…
A new LangGraph example in the open-source schemagate project cuts schema tokens sent to the model by 68% to 78% on a bundled 42-table demo database, sending 489 to 706 tokens per question instead of 2,199, with all thre…
OsFoundry's desktop app now provides a /rewind command that restores a local project folder to its exact state before a given AI agent turn, undoing file edits and deleting files the agent created. Before each agent writ…
A developer built a local mock server to test what happens when an HTTP client times out mid-request on a write operation, finding that the server-side write completes within milliseconds of the request body arriving—rou…
A developer tested whether a coding agent's CLAUDE.md rules are actually enforced by running a curl command the file claims is intercepted, finding it returned a proxy 403 rather than any hook-based block, while an allow…
A developer's documentation-only build examining SAP Integration Suite's MCP Gateway found that when the ERP vendor also hosts the agent tools, tools are generated from existing API definitions and exposed via a Streamab…
Swarms founder Kye Gomez released Swarms v17 "InterLink" on November 2nd, 2026, adding six communication channels and a validated fan-out workflow that give multi-agent systems a shared conversation space instead of pass…