Agents
Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision
arXiv:2610.16725v1 Announce Type: new Abstract: Improving an LLM agent requires knowing what to change when it fails. Similar failures can require different fixes, and resolving one problem can expose
arXiv:2610.16725v1 Announce Type: new Abstract: Improving an LLM agent requires knowing what to change when it fails. Similar failures can require different fixes, and resolving one problem can expose another. We introduce Trace-to-Architecture (T2A), a framework that uses execution trajectories to determine what to change in an agent's harness and when those changes apply. A development agent diagnoses failures using execution evidence from successful and failed tasks, revises the corresponding harness components, and then checks whether target tasks improve, selected successful tasks remain successful, and the edits are actually triggered. New execution evidence guides subsequent diagnosis and revision. Across ALFWorld, ScienceWorld, and AppWorld, T2A achieves the highest aggregate score for all three evaluated task agents, exceeding their respective strongest baselines by 6.2--30.3 points. We also integrate T2A's diagnosis and validation procedures into Meta-Harness, improving the resulting harnesses' mean ScienceWorld score by 21.6 points from the same starting harness.
Related
- GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity
- HELIX: Model-Harness Co-evolution for Recursive Self-Improvement
- Same Model, Different Harness: Different Coding-Agent Results
- Harness Evolution Hits a Ceiling: When Weight Training Should Begin
Source: arXiv cs.AI | 2026-10-15