New review paper argues code is how AI agents think and act, not just what they produce
A new review paper argues that the real bottleneck for autonomous AI agents is the software layer around the language model—tools, memory, testing, and permissions. DeepSeek is building a dedicated 'Harness' team in Beijing, confirming the formula: model + harness = AI agent.
Article intelligence
Key points
- The paper claims the bottleneck for AI agents is the software harness, not the model.
- Key components include tools, memory, testing, and permission boundaries.
- DeepSeek is forming a Harness team in Beijing, validating the model-plus-harness formula.
Why it matters
This matters because the paper claims the bottleneck for AI agents is the software harness, not the model.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
A new review paper argues that the real bottleneck for autonomous AI agents isn't the language model itself but the software layer wrapped around it. Tools, memory, testing, and permission boundaries turn a stateless model into a working agent. Deepseek is already building a dedicated "Harness" team in Beijing with a core formula that confirms the thesis: model plus harness equals AI agent.
The article New review paper argues code is how AI agents think and act, not just what they produce appeared first on The Decoder.