paper-with-me

Papers

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration

2025-05-30 · Qinglin Zhu, Runcong Zhao, Hanqi Yan, Yulan He, Yudong Chen, Lin Gui

Large Language Models (LLMs) struggle with complex reasoning due to limited diversity and inefficient search. We propose Soft Reasoning, an embedding-based search framework that optimises the embedding of the first token to guide generation. It combines (1) embedding perturbation for controlled exploration and (2) Bayesian optimisation to refine embeddings via a verifier-guided objective, balancing exploration and exploitation. This approach improves reasoning accuracy and coherence while avoiding reliance on heuristic search. Experiments demonstrate superior correctness with minimal computation, making it a scalable, model-agnostic solution.

📄 PDF Abstract BibTeX arXiv:2505.24688

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian OptimisationDiversityHeuristic Search

Similar Papers 제목 키워드 기반

Thought Space Explorer: Navigating and Expanding Thought Space for Large Language Model Reasoning

2024-10-31 · Jinghan Zhang, Fengran Mo, Xiting Wang, Kunpeng Liu

Recent advances in large language models (LLMs) have demonstrated their potential in handling complex reasoning tasks, which are usually achieved by constructing a thought chain to guide the model to solve the problem wi…

Language ModelingLanguage ModellingLarge Language Model

Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling

2025-07-31 · Trae Research Team, Pengfei Gao, Zhao Tian, Xiangxin Meng 외 arxiv

Software issue resolution is a critical challenge in software engineering and has garnered increasing attention in recent years. With the rapid advancement of large language models (LLMs), substantial progress has been m…

Autonomous Navigation System from Simultaneous Localization and Mapping

2021-12-14 · Micheal Caracciolo, Owen Casciotti, Christopher Lloyd, Ernesto Sola-Thomas 외

This paper presents the development of a Simultaneous Localization and Mapping (SLAM) based Autonomous Navigation system. The motivation for this study was to find a solution for navigating interior spaces autonomously. …

Autonomous NavigationSimultaneous Localization and Mapping

H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models

2026-04-15 · Cutter Dawes, Aryan Sharma, Angelos Ioannis Lagos, Shivam Raval arxiv

Representing and navigating hierarchy is a fundamental primitive of reasoning. Large language models have demonstrated proficiency in a wide variety of tasks requiring hierarchical reasoning, but there exists limited ana…

Mathematical Reasoning

Improving Latent Reasoning in LLMs via Soft Concept Mixing

2025-11-21 · Kang Wang, Xiangyu Duan, Tianyi Du arxiv

Unlike human reasoning in abstract conceptual spaces, large language models (LLMs) typically reason by generating discrete tokens, which potentially limit their expressive power. The recent work Soft Thinking has shown t…

Reinforcement Learning