Learning to Reason from Feedback at Test-Time

Understand

Solving complex tasks in a single attempt is challenging for large language models (LLMs).

• Iterative interaction with the environment and feedback is often required to achieve success, making effective feedback utilization a critical topic.
• Existing approaches either struggle with length generalization or rely on naive retries without leveraging prior information.
• In this paper, we introduce FTTT, a novel paradigm that formulates feedback utilization as an optimization problem at test time.