Microsoft Paper: Bash-Only Agents Beat Typed Tools by 20+ Points While Using Fewer Tokens
dair_ai · x · 2026-09-16
A Microsoft paper asks which tool interface to give an enterprise agent. Comparing five interfaces on TheAgentCompany and APEX-Agents with Opus-4.8 and GPT-5.5 — from typed tool catalogs, to bash alone, to programmatic tool calling — bash alone scored 21.8-24.5 points higher than typed tools on TheAgentCompany and 4.8-7.4 higher on APEX-Agents, while using 19-72% fewer tokens. Adding typed or agent-written tools on top of bash gave no measurable gain.
The authors recommend bash when execution can be sandboxed, and programmatic tool calling when compliance requires a fixed tool list.
More from coding & agent
- Removed from org, 5 years of commits gone: dev can't train agent on own history — DanielLockyer · 2026-09-16
- Workshop Sep 19: explainable AI apps with Neo4j, GraphRAG, Cypher and LLM agents — camerongreen95 · 2026-09-16
- LLM bug hunt finds full-stack attack chain to brick a hardware device — matthew_d_green · 2026-09-16
- Claude Code spotted testing Sessions Hub: unified local and cloud session management — testingcatalog · 2026-09-16
- Rowboat Launches as Open-Source Multiplayer AI Assistant That Ships Code via Claude Code — ycombinator · 2026-09-16
- Dev builds FailEcho, a scanner that finds agent failures repeating across runs — EvenAd1183 · 2026-09-16