Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

• URL: http://arxiv.org/abs/2412.18319v2
• Date: Tue, 31 Dec 2024 07:41:30 GMT
• Title: Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
• Authors: Huanjin Yao, Jiaxing Huang, Wenhao Wu, Jingyi Zhang, Yibo Wang, Shunyu Liu, Yingjie Wang, Yuxin Song, Haocheng Feng, Li Shen, Dacheng Tao,
• Abstract summary: We propose Collective Monte Carlo Tree Search (CoMCTS) for effective and efficient reasoning-path searching and learning. We construct Mulberry-260k, a multimodal dataset with a tree of rich, explicit and well-defined reasoning nodes for each question. We perform collective SFT to train our model, Mulberry, a series of MLLMs with o1-like step-by-step Reasoning and Reflection capabilities.
• Score: 74.46681227410038
• License:
• Abstract: 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), a new learning-to-reason method for MLLMs, which introduces the concept of collective learning into ``tree search'' for effective and efficient reasoning-path searching and learning. The core idea of CoMCTS is to leverage collective knowledge from multiple models to collaboratively conjecture, search and identify effective reasoning paths toward correct answers via four iterative operations including Expansion, Simulation and Error Positioning, Backpropagation, and Selection. Using CoMCTS, we construct Mulberry-260k, a multimodal dataset with a tree of rich, explicit and well-defined reasoning nodes for each question. With Mulberry-260k, we perform collective SFT to train our model, Mulberry, a series of MLLMs with o1-like step-by-step Reasoning and Reflection capabilities. Extensive experiments demonstrate the superiority of our proposed methods on various benchmarks. Code will be available at https://github.com/HJYao00/Mulberry

Related papers

• I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search [10.718560472954644]
  Introspective Monte Carlo Tree Search (I-MCTS) is a novel approach that iteratively expands tree nodes through an introspective process. This facilitates a continuous refinement of the node in the search tree, thereby enhancing the overall decision-making process. A hybrid rewarding mechanism is implemented to seamlessly transition the Q-value from LLM-estimated scores to actual performance scores.
  arXiv  Detail & Related papers  (2025-02-20T16:19:09Z)
• Prompting Large Language Models with Rationale Heuristics for Knowledge-based Visual Question Answering [6.745948705869626]
  We argue that prior methods do not sufficiently activate the capacities of Large Language Models (LLMs) We propose a framework called PLRH that Prompts LLMs with Rationale Heuristics for knowledge-based VQA.
  arXiv  Detail & Related papers  (2024-12-22T09:14:35Z)
• RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement [85.08223786819532]
  Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. We propose textbfRAG-Star, a novel RAG approach that integrates retrieved information to guide the tree-based deliberative reasoning process. Our experiments involving Llama-3.1-8B-Instruct and GPT-4o demonstrate that RAG-Star significantly outperforms previous RAG and reasoning methods.
  arXiv  Detail & Related papers  (2024-12-17T13:05:36Z)
• Enhancing LLM Reasoning with Reward-guided Tree Search [95.06503095273395]
  o1-like reasoning approach is challenging, and researchers have been making various attempts to advance this open area of research. We present a preliminary exploration into enhancing the reasoning abilities of LLMs through reward-guided tree search algorithms.
  arXiv  Detail & Related papers  (2024-11-18T16:15:17Z)
• MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs [78.5013630951288]
  This paper introduces techniques for advancing information retrieval with multimodal large language models (MLLMs) We first study fine-tuning an MLLM as a bi-encoder retriever on 10 datasets with 16 retrieval tasks. We propose modality-aware hard negative mining to mitigate the modality bias exhibited by MLLM retrievers.
  arXiv  Detail & Related papers  (2024-11-04T20:06:34Z)
• Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models [19.214387260667348]
  This paper introduces Monte-Carlo tree search for Zero-shot multi-hop Question Answering (MZQA), a framework based on Monte-Carlo tree search (MCTS) Unlike previous works, we propose a zero-shot prompting method, which relies solely on instructions without the support of hand-crafted few-shot examples that typically require domain expertise. We also introduce a behavioral cloning approach (MZQA-BC) trained on self-generated MCTS inference trajectories, achieving an over 10-fold increase in reasoning speed with bare compromise in performance.
  arXiv  Detail & Related papers  (2024-09-28T15:13:04Z)
• Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs [72.89652710634051]
  Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge. We introduce Tree-of-Traversals, a novel zero-shot reasoning algorithm that enables augmentation of black-box LLMs with one or more KGs.
  arXiv  Detail & Related papers  (2024-07-31T06:01:24Z)
• Autonomous Tree-search Ability of Large Language Models [58.68735916408101]
  Large Language Models have excelled in remarkable reasoning capabilities with advanced prompting techniques. Recent works propose to utilize external programs to define search logic, such that LLMs can perform passive tree search to solve more challenging reasoning tasks. We propose a new concept called autonomous tree-search ability of LLM, which can automatically generate a response containing search trajectories for the correct answer.
  arXiv  Detail & Related papers  (2023-10-14T14:14:38Z)
• Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training [37.79247073276239]
  Recent works like Tree-of-Thought (ToT) and Reasoning via Planning (RAP) aim to augment the reasoning capabilities of LLMs. We present an AlphaZero-like tree-search learning framework for LLMs (termed TS-LLM) We show how tree-search with a learned value function can guide LLM decoding.
  arXiv  Detail & Related papers  (2023-09-29T12:20:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.