#multi agent systems
7 articles
Latest
Eight Papers Advance LLM Agent Memory, Skills, and Multi-Agent Coordination
New methods address episodic memory retrieval, hierarchical skill reuse, tool library evolution, and heterogeneous agent routing through DAGs and induction.
LLM Agents Face Scale Problems on Sequential Decision Tasks
New benchmarks and multi-agent systems expose performance gaps when language models must reason through long chains of decisions.
Eight Papers Address Core Problems in Deployed LLM Agents
New research tackles memory management, model transitions, and tool accuracy in production agent systems.
Seven Papers Address Governance Crisis in Multi-Agent AI Systems
Researchers identify structural misalignment between what AI agents can do and what governance can control.
Enterprise AI Agent Systems Fail at Rates Up to 86.7 Percent
New research identifies coordination failures and specification mismatches as primary causes of multi-agent LLM system breakdowns.
Claude Code's Full Source Leaked via npm Source Map
500K lines of TypeScript exposing multi-agent orchestration, coordinator logic, and behavioral tracking systems.
AIPass Herald Logs Multi-Agent System Operations Daily
Open-source project publishes autonomous system behavior tracking for transparency and debugging.