paper-with-me

홈 › Papers

When in Doubt, Think Slow: Iterative Reasoning with Latent Imagination

2024-02-23 · Martin Benfeghoul, Umais Zahid, Qinghai Guo, Zafeirios Fountas

In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from planning and learning. We do so by applying iterative inference at decision-time, to fine-tune the inferred agent states based on the coherence of future state representations. Our approach achieves a consistent improvement in both reconstruction accuracy and task performance when applied to visual 3D navigation tasks. We go on to show that considering more future states further improves the performance of the agent in partially-observable environments, but not in a fully-observable one. Finally, we demonstrate that agents with less training pre-evaluation benefit most from our approach.

📄 PDF Abstract BibTeX arXiv:2402.15283

Code (0)

등록된 구현이 없습니다.

Tasks

Model-based Reinforcement Learning

Similar Papers 제목 키워드 기반

Do LLMs Really Think Step-by-step In Implicit Reasoning?

2024-11-24 · Yijiong Yu

It has been well-known that Chain-of-Thought can remarkably enhance LLMs' performance on complex tasks. However, because it also introduces slower inference speeds and higher computational costs, many researches have att…

Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt

2025-05-29 · Keqin Peng, Liang Ding, Yuanxin Ouyang, Meng Fang 외

Reasoning Large Language Models (RLLMs) have demonstrated impressive performance on complex tasks, largely due to the adoption of Long Chain-of-Thought (Long CoT) reasoning. However, they often exhibit overthinking -- pe…

Mathematical Reasoning

Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning

2025-06-26 · Xin Xu, Tianhao Chen, Fan Zhang, Wanlong Liu 외

While slow-thinking large language models (LLMs) exhibit reflection-like reasoning, commonly referred to as the "aha moment:, their ability to generate informative critiques and refine prior solutions remains limited. In…

A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law

2025-05-05 · Qianjun Pan, Wenkai Ji, Yuyang Ding, Junsong Li 외

This survey explores recent advancements in reasoning large language models (LLMs) designed to mimic "slow thinking" - a reasoning process inspired by human cognition, as described in Kahneman's Thinking, Fast and Slow. …

MathMedical Diagnosisscientific discoverySurvey+1

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

2024-10-31 · Ming Li, Yanhong Li, Tianyi Zhou

What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs), through the lens of gradient, when training with different responses and ini…