arXiv 2026 / LLM Agents

SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval

A benchmark-focused study of same-capability ambiguity in agent skill retrieval, where similar-looking skills must be distinguished by execution constraints and task fit.

Research area

Skill retrieval, semantic identifiers, NL2SQL benchmarks, and LLM serving systems are treated as capability surfaces that should be inspected before they are trusted.

Publication record

Authors
J Ding
Venue
arXiv preprint arXiv:2606.10388
Year
2026
Area
LLM Agents