🛰️ Daily AI Frontier
‹ back to 2026-08-18

The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks

Research LLM Agents

Ranking

Overall 79
Content 95
Popularity 43

Observed public metrics from 1 member.

Merged summary

TL;DR - This study models repository-scale coding as maintaining a graph of coupled facts, with unavailable facts creating “coherence debt.” Across seven models and five harnesses, fact availability—not context distance or extra token spending—primarily determined success.

  • Missing facts caused agents to fabricate files or guess values rather than leave work incomplete.
  • Prompt-supplied facts worked equally well whether near or far from the relevant edit.
  • Successful harnesses differed by over 10Ă— in token use because they reconstructed context at different rates.
  • Stale conventions could be worse than absent guidance, while memorized repository knowledge weakened read-based success metrics.

Sources (1)

The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks

arXiv cs.SE Bardia Mohammadi, Lars Klein, Aman Chadha, Akhil Arora, Laurent Bindschaedler 2026-08-17 arXiv:2608.16630
Public signals Hugging Face upvotes 0
Providers: Hugging Face · Upvotes 0 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-17 14:33:10.599132 UTC

TL;DR - This study models repository-scale coding as maintaining a graph of coupled facts, with unavailable facts creating “coherence debt.” Across seven models and five harnesses, fact availability—not context distance or extra token spending—primarily determined success.

  • Missing facts caused agents to fabricate files or guess values rather than leave work incomplete.
  • Prompt-supplied facts worked equally well whether near or far from the relevant edit.
  • Successful harnesses differed by over 10Ă— in token use because they reconstructed context at different rates.
  • Stale conventions could be worse than absent guidance, while memorized repository knowledge weakened read-based success metrics.
item →