Paper page - REPOT: Recoverable Program-of-Thought via Checkpoint Repair
… The following papers were recommended by the Semantic Scholar API Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents 2026 RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement 2026 SPEAR: Code-Augmented Agentic … …