RePoT recovers from PoT failures via deterministic verified replay and checkpoint repair, yielding +3 to +11pp gains on planning benchmarks and showing checkpoint state as the key recovery signal over error-only feedback.
Rebholz, and Mandy H \"u tter
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
REPOT: Recoverable Program-of-Thought via Checkpoint Repair
RePoT recovers from PoT failures via deterministic verified replay and checkpoint repair, yielding +3 to +11pp gains on planning benchmarks and showing checkpoint state as the key recovery signal over error-only feedback.