REPOT: Recoverable Program-of-Thought via Checkpoint Repair
:::info Stub — Full Engineering Breakdown Coming This paper was featured on Hugging Face Daily Papers on 2026-05-28 with 6 upvotes. A full breakdown with production viability rating, implementation notes, and honest limitations is being written. Subscribe to AI Letters → :::
| Authors | Parsa Mazaheri |
| Year | 2026 |
| HF Upvotes | 6 |
| arXiv | 2605.30052 |
| Download | |
| HF Page | View on Hugging Face |
Abstract
One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the trajectory. We introduce RePoT (Recoverable PoT): a deterministic verified replay that walks the plan through the environment to its first invalid transition, then one LLM call that resumes from the verified prefix. RePoT costs at most one extra LLM call on the ~14% of problems where PoT fails. RePoT beats PoT by +3 to +11pp across four closed-model configurations on PuzzleZoo-775 and peaks at 96.9% vs 86.3% on gpt-5.4-mini-medium; against the matched-budget PoT-retry baseline, RePoT wins decisively on Gemini (+3.8pp, 95% CI [+2.2,+5.4]), is within sampling noise on GPT-medium and Claude, and loses on GPT-mini -- a capability-scaling pattern we begin to address with Adaptive RePoT, a rule-based dispatcher that routes between suffix repair and a fresh PoT retry based on verified-prefix length (preliminary). We replicate on PlanBench Blocksworld (+1.1 to +11.4pp) and on four open-weights models (+3.3 to +20.0pp on three of four). On Derail-550, our controlled recovery benchmark, every condition with access to checkpoint information clears >=30% on GPT-medium and >=70% on Gemini, vs <=3.1% for error-only feedback -- showing that checkpoint information, not the specific verified-prefix tail, is the load-bearing recovery signal.
Engineering Breakdown
The Problem
One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the trajectory.
The Approach
We introduce RePoT (Recoverable PoT): a deterministic verified replay that walks the plan through the environment to its first invalid transition, then one LLM call that resumes from the verified prefix.
Key Results
On Derail-550, our controlled recovery benchmark, every condition with access to checkpoint information clears >=30% on GPT-medium and >=70% on Gemini, vs <=3.1% for error-only feedback -- showing that checkpoint information, not the specific verified-prefix tail, is the load-bearing recovery signal.
Research Areas
This paper contributes to the following areas of AI/ML engineering:
- Machine learning
- Deep learning
- Neural networks
- Model optimization
- AI systems
- Recoverable
:::tip Subscribe Get weekly breakdowns of papers like this in AI Letters - the newsletter for engineers building production AI systems. :::