Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Potamitis, Nearchos, Arora, Akhil
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910913487962112
author Potamitis, Nearchos
Arora, Akhil
author_facet Potamitis, Nearchos
Arora, Akhil
contents Recent advancements in large language models (LLMs) have catalyzed the development of general-purpose autonomous agents, demonstrating remarkable performance in complex reasoning tasks across various domains. This surge has spurred the evolution of a plethora of prompt-based reasoning frameworks. A recent focus has been on iterative reasoning strategies that refine outputs through self-evaluation and verbalized feedback. However, these strategies require additional computational complexity to enable models to recognize and correct their mistakes, leading to a significant increase in their cost. In this work, we introduce the concept of ``retrials without feedback'', an embarrassingly simple yet powerful mechanism for enhancing reasoning frameworks by allowing LLMs to retry problem-solving attempts upon identifying incorrect answers. Unlike conventional iterative refinement methods, our method does not require explicit self-reflection or verbalized feedback, simplifying the refinement process. Our findings indicate that simpler retrial-based approaches often outperform more sophisticated reasoning frameworks, suggesting that the benefits of complex methods may not always justify their computational costs. By challenging the prevailing assumption that more intricate reasoning strategies inherently lead to better performance, our work offers new insights into how simpler, more efficient approaches can achieve optimal results. So, are retrials all you need?
format Preprint
id arxiv_https___arxiv_org_abs_2504_12951
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback
Potamitis, Nearchos
Arora, Akhil
Computation and Language
Artificial Intelligence
Machine Learning
Recent advancements in large language models (LLMs) have catalyzed the development of general-purpose autonomous agents, demonstrating remarkable performance in complex reasoning tasks across various domains. This surge has spurred the evolution of a plethora of prompt-based reasoning frameworks. A recent focus has been on iterative reasoning strategies that refine outputs through self-evaluation and verbalized feedback. However, these strategies require additional computational complexity to enable models to recognize and correct their mistakes, leading to a significant increase in their cost. In this work, we introduce the concept of ``retrials without feedback'', an embarrassingly simple yet powerful mechanism for enhancing reasoning frameworks by allowing LLMs to retry problem-solving attempts upon identifying incorrect answers. Unlike conventional iterative refinement methods, our method does not require explicit self-reflection or verbalized feedback, simplifying the refinement process. Our findings indicate that simpler retrial-based approaches often outperform more sophisticated reasoning frameworks, suggesting that the benefits of complex methods may not always justify their computational costs. By challenging the prevailing assumption that more intricate reasoning strategies inherently lead to better performance, our work offers new insights into how simpler, more efficient approaches can achieve optimal results. So, are retrials all you need?
title Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2504.12951