Metraipolis › archive › dc_aa91f156c52e

Answer Probing-Guided Search for Diverse Solution Exploration of LLMs — arXiv:2608.30345

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30345
License (as archived)
CC0-1.0
Archived
2026-10-17T07:44:36.642Z
SHA-256 of the archived text
ba36c424856d51c7e29284cd43ded821c6e5a48b3fec5d69c223c79e1bb0e462
Stable URL of this page
https://metraipolis.com/documento/dc_aa91f156c52e

How to cite

Answer Probing-Guided Search for Diverse Solution Exploration of LLMs — arXiv:2608.30345 — arXiv (en), https://arxiv.org/abs/2608.30345 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa91f156c52e (Metraipolis archive dc_aa91f156c52e, sha256 ba36c424856d51c7e29284cd43ded821c6e5a48b3fec5d69c223c79e1bb0e462)
BibTeX
@misc{dcaa91f156c52e,
  title = {Answer Probing-Guided Search for Diverse Solution Exploration of LLMs — arXiv:2608.30345},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30345},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa91f156c52e; sha256 ba36c424856d51c7e29284cd43ded821c6e5a48b3fec5d69c223c79e1bb0e462},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30345. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.30345 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:28:26.596Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).