SOURCE-LINKED INTELLIGENCE

Answer Probing-Guided Search for Diverse Solution Exploration of LLMs

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

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 genu

Read original source ↗ Open in workspace

recordType

paper

region

Global