arXiv:2602. 13935v2 Announce Type: replace Abstract: While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries.
By Yangxinyu Xie, Tao Wang, Soham Mallick, Yan Sun, Georgy Noarov, Mengxin Yu, Tanwi Mallick, Weijie J. Su, Edgar Dobriban
arXiv:2608. 14425v1 Announce Type: new Abstract: LLM evaluations often use fixed sampling budgets, testing every item the same number of times even after estimates are precise.
By Toby D. Pilditch
arXiv:2607. 06720v1 Announce Type: new Abstract: Training large language models (LLMs) with extended reasoning has enabled in-context search, in which models iteratively generate, critique, and revise solution attempts.
By Yotam Wolf, Noam Wies, Amnon Shashua
The paper introduces Adaptive Self-Consistency (ASC), a method that treats large language models as grey-boxes by leveraging the full answer distribution from log‑probabilities rather than single sampled answers. It formulates inference as sequential mode identification with distribution‑valued observations, proving that this approach never performs worse than traditional black‑box sampling and can stop earlier. The proposed ASC‑D algorithm, a betting‑based stopping rule, achieves significant reductions in required trajectories—up to 95.6% fewer—while attaining the best fixed‑budget correct‑certification rates on MMLU‑Redux across three open‑source models.
By Jingkai Huang, Yunfan Zhang, Will Ma, Weihua Zhou, Zhengyuan Zhou
arXiv:2602.02427v3 Announce Type: replace
Abstract: Large Language Models (LLMs) have achieved significant breakthroughs across various domains, but they can still produce unreliable or misleading ou...
By Qihao Wen, Jiahao Wang, Yang Nan, Pengfei He, Ravi Tandon, Han Xu
Self-consistency samples many reasoning trajectories and aggregates their final answers, treating the LLM as a black box that returns one answer per trajectory. Yet the final answer of each trajectory...