8 Papers on the Agent Harness Progress You Need to Know

Automated excerpt

Over the past two months, a cluster of papers has appeared on arXiv from teams at Alibaba's DreamX group, Meta AI, Google Cloud, ByteDance Seed, and others — all aimed at the same target: the agent harness, the runtime layer wrapped around the model that handles context construction, state management, tool invocation, error recovery, and result verification. Same conclusion from both papers: state belongs outside the conversation history. Long-horizon execution needs explicit state management.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.