{"paper":{"title":"ALIVE: Awakening LLM Reasoning via Adversarial Learning and Instructive Verbal Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jing Ye, Xinpei Zhao, Yiwen Duan","submitted_at":"2026-02-05T09:20:23Z","abstract_excerpt":"The quest for expert-level reasoning in Large Language Models (LLMs) has been hampered by a persistent \\textit{reward bottleneck}: traditional reinforcement learning (RL) relies on scalar rewards that are \\textbf{costly} to scale, \\textbf{brittle} across domains, and \\textbf{blind} to the underlying logic of a solution. This reliance on external, impoverished signals prevents models from developing a deep, self-contained understanding of reasoning principles. We introduce \\textbf{ALIVE} (\\emph{Adversarial Learning with Instructive Verbal Evaluation}), a hands-free alignment framework that move"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05472","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.05472/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}