Answer Probing-Guided Search for Diverse Solution Exploration of LLMs

• URL: http://arxiv.org/abs/2608.30345v1
• Date: Mon, 31 Aug 2026 07:01:36 GMT
• Title: Answer Probing-Guided Search for Diverse Solution Exploration of LLMs
• Abstract summary: Large Language Models (LLMs) tend to converge on a single high-confidence solution during inference.<n>We propose Answer Probing-Guided Tree Search (APTS), which guides the tree search by the probed answers' hidden state similarity and perplexity.
• Score: 61.647721732856034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating multiple diverse and high-quality solutions is valuable for many applications, such as code-test generation and drug discovery. However, Large Language Models (LLMs) tend to converge on a single high-confidence solution during inference, limiting exploration of alternative valid solution paths. Existing test-time methods promote diversity through tree-like search and prune semantically similar branches using response-level semantic embeddings. However, we find that such embeddings are easily confounded by linguistic and stylistic similarities, making it difficult to distinguish genuinely distinct solution paths. To address this, we introduce Answer Probing, which probes the potential answer an LLM would reach from an intermediate reasoning path. We demonstrate that the hidden states of probed answers more effectively differentiate distinct solution paths than semantic embeddings, and the perplexity of probed answers serves as a practical proxy for reasoning correctness. Based on these findings, we propose Answer Probing-Guided Tree Search (APTS), which guides the tree search by the probed answers' hidden state similarity and perplexity. Experiments on three reasoning tasks across two LLMs show that APTS consistently enhances solution diversity, demonstrating its effectiveness and robustness.

Related papers

• Reinforced Efficient Reasoning via Semantically Diverse Exploration [73.41112984160992]
  Reinforcement learning with verifiable rewards (RLVR) has proven effective in enhancing the reasoning of large language models (LLMs)<n>We propose reinforced efficient reasoning via semantically diverse explorations, i.e., ROSE, for LLMs.<n>Our method incorporates a semantic-entropy-based branching strategy and an $varepsilon$-exploration mechanism.
  arXiv  Detail & Related papers  (2026-01-08T15:56:44Z)
• Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction [57.67217258741752]
  Thinker is a hierarchical thinking model for deep search through multi-turn interaction.<n>It decomposes complex problems into independently solvable sub-problems.<n> dependencies between sub-problems are passed as parameters via these logical functions.
  arXiv  Detail & Related papers  (2025-11-11T07:48:45Z)
• MIRAGE: Multi-hop Reasoning with Ambiguity Evaluation for Illusory Questions [25.695038634265]
  Real-world Multi-hop Question Answering (QA) often involves ambiguity that is inseparable from the reasoning process itself.<n>This ambiguity creates a distinct challenge, where multiple reasoning paths emerge from a single question.<n>We introduce MultI-hop Reasoning with AmbiGuity Evaluation for Illusory Questions (MIRAGE) to analyze and evaluate this challenging intersection.
  arXiv  Detail & Related papers  (2025-09-26T07:31:01Z)
• Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models [0.0]
  This paper introduces Semantic Divergence Metrics (SDM), a novel framework for detecting Faithfulness Hallucinations.<n>A heatmap of topic co-occurances between prompts and responses can be viewed as a quantified two-dimensional visualization of the user-machine dialogue.
  arXiv  Detail & Related papers  (2025-08-13T20:55:26Z)
• Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models [8.295475330195993]
  We propose Semantic Exploration with Adaptive Gating (SEAG) to explore semantically identical paths.<n>SEAG significantly improves accuracy by 4.3% on average while requiring only 31% of computational costs.<n>Our code is available at https://github.com/ml-postech/SEAG-semantic-exploration-with-adaptive-gating.
  arXiv  Detail & Related papers  (2025-01-10T07:02:43Z)
• FLARE: Faithful Logic-Aided Reasoning and Exploration [47.46564769245296]
  We introduce a novel approach for traversing the problem space using task decompositions.<n>We use the Large Language Models to plan a solution, soft-formalise the query into facts and predicates using a logic programming code.<n>Our method allows us to compute the faithfulness of the reasoning process w.r.t. the generated code and analyse the steps of the multi-hop search without relying on external solvers.
  arXiv  Detail & Related papers  (2024-10-14T19:39:11Z)
• PathFinder: Guided Search over Multi-Step Reasoning Paths [80.56102301441899]
  We propose PathFinder, a tree-search-based reasoning path generation approach. It enhances diverse branching and multi-hop reasoning through the integration of dynamic decoding. Our model generalizes well to longer, unseen reasoning chains, reflecting similar complexities to beam search with large branching factors.
  arXiv  Detail & Related papers  (2023-12-08T17:05:47Z)
• A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering [60.768146126094955]
  Weakly supervised question answering usually has only the final answers as supervision signals. There may exist many spurious solutions that coincidentally derive the correct answer, but training on such solutions can hurt model performance. We propose to explicitly exploit such semantic correlations by maximizing the mutual information between question-answer pairs and predicted solutions.
  arXiv  Detail & Related papers  (2021-06-14T05:47:41Z)
• Learning by Fixing: Solving Math Word Problems with Weak Supervision [70.62896781438694]
  Previous neural solvers of math word problems (MWPs) are learned with full supervision and fail to generate diverse solutions. We introduce a textitweakly-supervised paradigm for learning MWPs. Our method only requires the annotations of the final answers and can generate various solutions for a single problem.
  arXiv  Detail & Related papers  (2020-12-19T03:10:21Z)
• Explanation Generation for Multi-Modal Multi-Agent Path Finding with Optimal Resource Utilization using Answer Set Programming [1.7132914341329848]
  The real-world applications of mMAPF require flexibility and explainability. This paper introduces a method for generating explanations for queries regarding the feasibility and optimality of solutions.
  arXiv  Detail & Related papers  (2020-08-08T18:34:34Z)

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.