Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The release gives developers a publicly modifiable interface between trading commands and AI tooling, with live-order security caveats flagged as a factor that could affect the reliability of systems built on it.
MAFP extends LLM multi-agent systems beyond task decomposition into genuinely interdependent decision-making, a class of problems the paper shows existing frameworks fail to address.
The benchmark reveals that frontier AI models — including those augmented with Code Agents — effectively fail at large-scale game project engineering, with runtime pass rates collapsing to 5.7%, exposing architectural design as an unsolved bottleneck that compilation-focused improvements cannot address.
The project offers an open alternative to a capability that OpenAI restricts to Enterprise customers, making it accessible outside that paid tier.
The system replaces unconstrained LLM escalation with a structured, forecast-grounded pipeline and introduces a regulator-aligned evaluation metric for false interventions — two gaps the authors identify as absent from existing DeFi supervision approaches.
The HTLC-based model removes the need for a trusted custodian in multi-leg agent trades by making conditionality native to the lock structure itself, so that no coordinator is added as the number of trade legs grows.
The `/automate` skill offloads the manual work of configuring automation triggers and tooling to the agent, letting users set up automations through natural language alone.
A new addition to the hosted MCP server space, covering social media scheduling across 11 platforms without requiring users to manage their own infrastructure.
Sierra's expansion from customer support to the full customer lifecycle — combined with a commission-based pricing model — illustrates a concrete shift in how AI agents are being deployed and monetized beyond traditional service use cases.
Draft introduces a git-backed, human-verified context layer that lets multiple agents and team members share the same AI session context, replacing ad-hoc per-user context management with a collaborative, auditable workflow.