Magellan: Guided MCTS for Latent Space Exploration and Novelty Generation

• URL: http://arxiv.org/abs/2510.21341v1
• Date: Fri, 24 Oct 2025 11:09:59 GMT
• Title: Magellan: Guided MCTS for Latent Space Exploration and Novelty Generation
• Authors: Lufan Chang,
• Abstract summary: Large Language Models (LLMs) often struggle with generating truly innovative ideas.<n>We introduce textbfMagellan, a novel framework that reframes creative generation as a principled, guided exploration.<n>Our work shows that for creative discovery, a principled, guided search is more effective than unconstrained agency.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) often struggle with generating truly innovative ideas, typically defaulting to high-probability, familiar concepts within their training data's "gravity wells." While advanced search-based methods like Tree of Thoughts (ToT) attempt to mitigate this, they are fundamentally limited by their reliance on unprincipled, inconsistent self-evaluation heuristics to guide exploration. To address this gap, we introduce \textbf{Magellan}, a novel framework that reframes creative generation as a principled, guided exploration of an LLM's latent conceptual space. At its core, Magellan employs Monte Carlo Tree Search (MCTS) governed by a hierarchical guidance system. For long-range direction, a "semantic compass" vector, formulated via orthogonal projection, steers the search towards relevant novelty. For local, step-by-step decisions, a landscape-aware value function replaces flawed self-evaluation with an explicit reward structure that balances intrinsic coherence, extrinsic novelty, and narrative progress. Extensive experiments demonstrate that Magellan significantly outperforms strong baselines, including ReAct and ToT, in generating scientific ideas with superior plausibility and innovation. Our work shows that for creative discovery, a principled, guided search is more effective than unconstrained agency, paving the way for LLMs to become more capable partners in innovation.

Related papers

• LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval [74.72139580745511]
  LaSER is a novel self-distillation framework that internalizes explicit reasoning into the latent space of retrievers.<n>Our method successfully combines the reasoning depth of explicit CoT pipelines with the inference efficiency of standard dense retrievers.
  arXiv  Detail & Related papers  (2026-03-02T04:11:18Z)
• DeepInnovator: Triggering the Innovative Capabilities of LLMs [41.60038455664918]
  DeepInnovator is a training framework designed to trigger the innovative capability of Large Language Models (LLMs)<n>We construct an automated data extraction pipeline to extract structured research knowledge from a vast corpus of unlabeled scientific literature.<n>We introduce a Next Idea Prediction'' training paradigm, which models the generation of research ideas as an iterative process of continuously predicting, evaluating, and refining plausible and novel next idea.
  arXiv  Detail & Related papers  (2026-02-21T18:07:18Z)
• Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards [33.42935710088259]
  We introduce MERCI (Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards), a novel RL algorithm that augments policy optimization with a principled intrinsic reward.<n>We show that MERCI encourages richer and more varied chains of thought, significantly improves performance over strong baselines, and helps the policy escape local routines to discover better solutions.
  arXiv  Detail & Related papers  (2025-10-18T18:57:26Z)
• Large Language Models as Innovators: A Framework to Leverage Latent Space Exploration for Novelty Discovery [19.394116388173885]
  Large language models (LLMs) often struggle to produce outputs that are both novel and relevant.<n>We propose a model-agnostic latent-space ideation framework that enables controlled, scalable creativity.
  arXiv  Detail & Related papers  (2025-07-18T12:54:28Z)
• Harnessing Large Language Models for Scientific Novelty Detection [49.10608128661251]
  We propose to harness large language models (LLMs) for scientific novelty detection (ND)<n>To capture idea conception, we propose to train a lightweight retriever by distilling the idea-level knowledge from LLMs.<n> Experiments show our method consistently outperforms others on the proposed benchmark datasets for idea retrieval and ND tasks.
  arXiv  Detail & Related papers  (2025-05-30T14:08:13Z)
• MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search [61.11836311160951]
  We introduce MCTS-RAG, a novel approach that enhances the reasoning capabilities of small language models on knowledge-intensive tasks.<n>Unlike standard RAG methods, which typically retrieve information independently from reasoning, MCTS-RAG combines structured reasoning with adaptive retrieval.<n>This integrated approach enhances decision-making, reduces hallucinations, and ensures improved factual accuracy and response consistency.
  arXiv  Detail & Related papers  (2025-03-26T17:46:08Z)
• A Survey on Post-training of Large Language Models [185.51013463503946]
  Large Language Models (LLMs) have fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration.<n>These challenges necessitate advanced post-training language models (PoLMs) to address shortcomings, such as restricted reasoning capacities, ethical uncertainties, and suboptimal domain-specific performance.<n>This paper presents the first comprehensive survey of PoLMs, systematically tracing their evolution across five core paradigms: Fine-tuning, which enhances task-specific accuracy; Alignment, which ensures ethical coherence and alignment with human preferences; Reasoning, which advances multi-step inference despite challenges in reward design; Integration and Adaptation, which
  arXiv  Detail & Related papers  (2025-03-08T05:41:42Z)
• CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models Reasoning [0.7009487789080343]
  Chain-of-Associated-Thoughts (CoAT) framework is inspired by the human ability to constantly associate and replenish knowledge during thinking.<n>By combining the structured exploration capabilities of MCTS with the adaptive learning capacity of associative memory, CoAT significantly expands the LLM search space.<n>CoAT achieves over 10% performance improvement on open-source multi-hop reasoning datasets.
  arXiv  Detail & Related papers  (2025-02-04T15:10:33Z)
• A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models [100.16387798660833]
  Oogiri game is a creativity-driven task requiring humor and associative thinking.<n>LoTbench is an interactive, causality-aware evaluation framework.<n>Results show that while most LLMs exhibit constrained creativity, the performance gap between LLMs and humans is not insurmountable.
  arXiv  Detail & Related papers  (2025-01-25T09:11:15Z)
• Learning to Generate Research Idea with Dynamic Control [21.30777644522451]
  Large language models (LLMs) have shown promise in generating hypotheses and research ideas.<n>We introduce a novel framework that employs a two-stage approach combiningSupervised Fine-Tuning (SFT) and controllable Reinforcement Learning (RL)<n>Our framework provides a balanced approach to research ideation, achieving high-quality outcomes by dynamically navigating the trade-offs among novelty, feasibility, and effectiveness.
  arXiv  Detail & Related papers  (2024-12-19T08:28:18Z)
• 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.<n>We propose textbfRAG-Star, a novel RAG approach that integrates retrieved information to guide the tree-based deliberative reasoning process.<n>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)
• Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas [30.3756058589173]
  We introduce an enhanced planning and search methodology designed to boost the creative potential of large language models (LLMs) Our framework substantially elevates the quality of generated ideas, particularly in novelty and diversity. Our method outperforms the current state-of-the-art, generating at least 2.5 times more top-rated ideas based on 170 seed papers in a Swiss Tournament evaluation.
  arXiv  Detail & Related papers  (2024-10-18T08:04:36Z)

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.