相关论文: THOUGHTSCULPT: Reasoning with Intermediate Revisio…

In this work, we aim to develop an MLLM that understands and solves questions by learning to create each intermediate step of the reasoning involved till the final answer. To this end, we propose Collective Monte Carlo Tree Search (CoMCTS),…

Recent advancements in large language models (LLMs) have demonstrated their impressive abilities in various reasoning and decision-making tasks. However, the quality and coherence of the reasoning process can still benefit from enhanced…

While the recently introduced Tree of Thoughts (ToT) has heralded advancements in allowing Large Language Models (LLMs) to reason through foresight and backtracking for global decision-making, it has overlooked the inherent local…

Recent advancements in large language models (LLMs) have shown remarkable potential in automating machine learning tasks. However, existing LLM-based agents often struggle with low-diversity and suboptimal code generation. While recent work…

Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in…

Monte Carlo Tree Search (MCTS) is an effective test-time compute scaling (TTCS) method for improving the reasoning performance of large language models, but its highly variable execution time leads to severe long-tail latency in practice.…

Tree search has become as a representative framework for test-time reasoning with large language models (LLMs), exemplified by methods such as Tree-of-Thought and Monte Carlo Tree Search. However, it remains difficult to provide instant and…

In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understanding and advanced reasoning capabilities. However,…

Monte Carlo Tree Search (MCTS) is a powerful approach to designing game-playing bots or solving sequential decision problems. The method relies on intelligent tree search that balances exploration and exploitation. MCTS performs random…

Large Language Models (LLMs) face significant accuracy degradation due to insufficient reasoning ability when dealing with complex and abstract tasks. Thought structures such as Chain of Thought (CoT) and Tree of Thought (ToT) focus on…

Effective decision-making and problem-solving in conversational systems require the ability to identify and acquire missing information through targeted questioning. A key challenge lies in efficiently narrowing down a large space of…

We introduce a novel approach to the executable semantic object rearrangement problem. In this challenge, a robot seeks to create an actionable plan that rearranges objects within a scene according to a pattern dictated by a natural…

Current literature, aiming to surpass the "Chain-of-Thought" approach, often resorts to external modi operandi involving halting, modifying, and then resuming the generation process to boost Large Language Models' (LLMs) reasoning…

Monte Carlo tree search (MCTS) is one of the most capable online search algorithms for sequential planning tasks, with significant applications in areas such as resource allocation and transit planning. Despite its strong performance in…

Synthetic high-quality multi-step reasoning data can significantly enhance the performance of large language models on various tasks. However, most existing methods rely on rejection sampling, which generates trajectories independently and…

With the advancement of large language models (LLMs), diverse time series analysis tasks are reformulated as time series question answering (TSQA) through a unified natural language interface. However, existing LLM-based approaches largely…

Multimodal Chain of Thought (MCoT) is a popular prompting strategy for improving the performance of multimodal large language models (MLLMs) across a range of complex reasoning tasks. Despite its popularity, there is a notable absence of…

Chain-of-Thought (CoT) prompting has significantly enhanced the mathematical reasoning capabilities of Large Language Models. We find existing fine-tuning datasets frequently suffer from the "answer right but reasoning wrong" probelm, where…

Discovering novel catalysts requires complex reasoning involving multiple chemical properties and resultant trade-offs, leading to a combinatorial growth in the search space. While large language models (LLM) have demonstrated novel…

Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize…