pith. sign in

These represent tool-chain or computation errors downstream of successful navigation

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

The Amazing Agent Race: Strong Tool Users, Weak Navigators

cs.AI · 2026-04-11 · unverdicted · novelty 7.0

The Amazing Agent Race benchmark shows LLM agents are strong at tool execution but weak at navigating complex Wikipedia-based DAG tool chains, with best accuracy at 37.2% dominated by navigation errors.

citing papers explorer

Showing 1 of 1 citing paper.

  • The Amazing Agent Race: Strong Tool Users, Weak Navigators cs.AI · 2026-04-11 · unverdicted · none · ref 2

    The Amazing Agent Race benchmark shows LLM agents are strong at tool execution but weak at navigating complex Wikipedia-based DAG tool chains, with best accuracy at 37.2% dominated by navigation errors.