Agents
I like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the to…
I like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the tool boundary: - what context you pass - when tools are provid
I like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the tool boundary: - what context you pass - when tools are provided - how you recover from failure - what gets measured afterward That’s the loop we’re building around deepagents (the orchestration logic) + LangSmith (how you measure) Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses — new paper (arXiv, 4 Sep 2026; accepted EMNLP 2026). https://arxiv.org/abs/2609.05736 Treats harness optimization around a fixed model as budgeted selection: edits are guarded intercepts at the tool boundary, not …
Related
- memory is just context -> the harness decides what gets remembered, how, and when memory ownership = agent ownership deepagents lets you own…
- The ‘agent harness’ is essentially the new runtime. It’s like a lightweight OS around an LLM—handling memory, tool calls, retries, and contr…
- 'Agents = model + harness + context' is a much better mental model than treating the LLM as the entire product. The model provides capabilit…
- @hwchase17 is right, memory creates lock-in. But not just conversations. Tool registries, hooks, agent conventions -> that's harness memory …
Source: Harrison Chase (X) | 2026-09-09