Context Is a Pipeline, Not a Window: Information Attrition in LLM Agent Harnesses
Across 720 runs the largest prompt was 23k tokens against a 400k window (5.75%).
5.75%share of the context window used by the largest prompt across 720 agent runs
Agent harnesses
Week 44 · 26 Oct-1 Nov
3 sources filed · EN 3
A A Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents
Top-1 accuracy (PR@1) on three mid-tier models: simple harnesses 65-77%, published agents 16-53%, non-LLM methods 6-39%.
65-77%top-1 root-cause accuracy of simple harnesses on three mid-tier models
A Build or Adopt? Custom-Built vs. General-Purpose LLM Agent Harnesses for Automotive GUI Testing
Volvo benchmark (66 tasks): all configurations succeed in 55-61% of runs; same-model differences of -4.5 to -0.8 points, none significant.
2.6 to 10.7 timesinference cost per task of general-purpose harnesses versus the in-house one, same model, on Volvo's infotainment tests