AI Agents

Researchers introduced Onnes, a physics-grounded multi-agent LLM simulator for cryogenic fault diagnosis in quantum computing infrastructure. In controlled evaluations, a zero-shot LLM panel matched a supervised ML class…

Researchers introduced StateFuse, a conflict-aware replicated memory contract for multi-agent systems that preserves contradictory observations instead of collapsing them. In evaluations, StateFuse enabled safer abstenti…

Researchers introduced Light-Omni, a multimodal agent framework for reflexive video understanding that uses dual contextual states to avoid costly iterative reasoning. It achieved a 2.4% accuracy gain over M3-Agent with …

Researchers tested how persona prompts affect large language model agents in an iterated Split or Steal game, finding that mutual cooperation dominated in roughly 74% of rounds across 160 sessions. Model choice significa…

Researchers introduced FirstResearch, a framework that generates auditable research questions for LLM scientific discovery agents by producing a structured Research Question Certificate. In evaluations, FirstResearch out…

Researchers introduced ArtisanCAD, an industrial-level CAD agent that uses expert-grounded knowledge distillation to convert ambiguous text prompts into executable CAD programs. The system leverages a CAD intermediate re…

Researchers introduced AgenticAI-Supervisor, an API and UI-driven RL Gym environment that decouples environment creation from scalable execution for training LLM-based autonomous agents. The platform generates high-fidel…

Researchers at arXiv found that steering vectors extracted from heading-anchor positions in tool-augmented large language models can suppress unnecessary tool use across five open-source models and three domains. However…

Researchers propose TurnOPD, a turn-level budgeting strategy for efficient on-policy distillation of long-horizon language agents. The method addresses inefficiencies in vanilla agent OPD by using adaptive rollout-depth …

Researchers introduced CanvasAgent, a multimodal agent that orchestrates multiple visual tools for complex image creation and editing, along with the CanvasCraft dataset containing 140K annotated trajectories. The agent …

Researchers formalize the execution harness of LLM agents as a learnable control layer using offline reinforcement learning, training a lightweight controller with advantage-weighted regression to improve verification be…

Researchers introduced FedPPO-PG, a federated multi-agent reinforcement learning framework for transient stability control in smart grids. The system achieved 100% stabilization in simulations on the IEEE 39-bus benchmar…

Developer Tommy Tran released Traceburn, a local-first tracer and efficiency profiler for AI agents, which identified 69% avoidable spend in a test run by suggesting prompt caching. The open-source tool, built on OpenAI …

The Model Context Protocol (MCP) enables AI assistants to interact with external tools and data sources through standardized servers. A developer demonstrates how to build MCP servers using the official SDK, with example…

Kortix launched an open-source AI platform that treats an entire company as a Git repository, enabling teams to manage agents, skills, connectors, and memory as version-controlled files. The platform provides isolated ex…

Arcade and Manufact have launched agent authorization and MCP hosting products in cloud marketplaces, signaling that agent gateways are emerging as a distinct enterprise category. Nutanix also released its Agent Gateway …

Magnus, a former SVP of Engineering at Lark and VP Engineering at Strive Health, is now Chief Tentacle Officer at Groktopus LLC, writing about AI and the future of work. He has been actively developing open-source AI too…

LLM code generation enthusiasts are creating 'vibe forks'—reimplementations of existing projects using AI coding tools—raising concerns about the value of source code as a moat. However, curation, trust, and deployment h…

Researchers introduced agent data injection attacks (ADI), a new category of indirect prompt injection that disguises malicious data as trusted data to trick AI agents into executing unintended actions. The attacks bypas…

A developer from LaiCai has proposed a context contract for AI-assisted Android automation, defining the minimum set of facts—such as target environment, device state, app package, and node schema—that an AI assistant li…