EvoCode-Bench shows that single-round success rates for coding agents exceed multi-turn persistent execution rates by 22-40 points, with performance dropping below half of round-1 levels by round 5 across 13 evaluated agents.
They never inspect source code structure, function names, or file organization
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
-
EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
EvoCode-Bench shows that single-round success rates for coding agents exceed multi-turn persistent execution rates by 22-40 points, with performance dropping below half of round-1 levels by round 5 across 13 evaluated agents.