CTA framework detects 522 skill influence patterns in LLM agent traces across 49 tasks where average pass rate shifts only +0.3%, exposing evaluation gaps in behavioral effects like template copying and excess planning.
Introducing SWE-bench Verified
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Counterfactual Trace Auditing of LLM Agent Skills
CTA framework detects 522 skill influence patterns in LLM agent traces across 49 tasks where average pass rate shifts only +0.3%, exposing evaluation gaps in behavioral effects like template copying and excess planning.