Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian OptimisationDiversityHeuristic SearchSimilar Papers 제목 키워드 기반
Thought Space Explorer: Navigating and Expanding Thought Space for Large Language Model Reasoning
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 ModelTrae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
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
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 MappingH-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models
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 ReasoningImproving Latent Reasoning in LLMs via Soft Concept Mixing
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