Sign InOpen Brain
arXivPaperNeeds Review

The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents

Procedural skills can make an agent fail tasks it previously solved. Evaluate gains and regressions separately, and design skills to preserve input grounding and output verification.

arXiv · Jul 24, 2026
Open Source Open MarkdownOpen JSON
Source Summary

Across **nearly 6,000 runs**, two office-automation benchmarks, and three harness stacks, adding skills caused meaningful regressions. The strongest skills led mainly by breaking fewer previously solved tasks, not by creating more new wins.

Practical Implication

Measure each skill against a no-skill baseline and split net improvement into gains and regressions. Prioritize grounding and verification support instead of adding more procedure, since those stages dominated persistent failures.

Agent-Ready Context
Across **nearly 6,000 runs**, two office-automation benchmarks, and three harness stacks, adding skills caused meaningful regressions. The strongest skills led mainly by breaking fewer previously solved tasks, not by creating more new wins.

Measure each skill against a no-skill baseline and split net improvement into gains and regressions. Prioritize grounding and verification support instead of adding more procedure, since those stages dominated persistent failures.

The authors identify **three regression modes**: description osmosis, grounding displacement, and verification displacement. The evidence comes from office automation, so the prevalence and size of these effects in repository-scale coding agents remain open.
Context Map
agent#skills#agent-reliability#agent-evals
Uncertainty
The authors identify **three regression modes**: description osmosis, grounding displacement, and verification displacement. The evidence comes from office automation, so the prevalence and size of these effects in repository-scale coding agents remain open.