Agents Can Reason. They Still Can't Really Search.
Modern agents can write code, call APIs, draft a memo, and pass a benchmark. That part is real. Put one in front of a clean, well-scoped task and it can look...
Agents Can Reason. They Still Can't Really Search.
dipkumar.devAgents have a search problem across the whole stack: web search, RAG, tool discovery, skills/workflow loading, and even context compaction.