LLM Agents
MIRIX-2.0: Multi-Agent Memory System Achieves Benchmark-Leading Accuracy
MIRIX-2.0, a multi-agent memory system, sets new standards in QA and procedural benchmarks with high accuracy and efficiency, as detailed in a new AI paper.
LLM Agents
WikiTrace: Evidence-Linked Memory System Enhances LLM Agent Performance
WikiTrace, an evidence-linked memory system, reduces memory-induced degradation in LLM agents, outperforming prior methods on five benchmarks.
LLM Agents
LangChain Introduces Agent Protocol to Enhance Interoperability for LLM Agents
LangChain unveils Agent Protocol, a standardized interface for agent communication, enhancing interoperability across frameworks like AutoGen, CrewAI, and more.