AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin

[2505.14264] AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2505.14264 (cs) [Submitted on 20 May 2025 ( v1 ), last revised 14 Apr 2026 (this version, v3)] Title: AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin Authors: Jian Xiong , Jingbo Zhou , Jingyong Ye , Qiang Huang , Dejing Dou View a PDF of the paper titled AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin, by Jian Xiong and 4 other authors View PDF HTML (experimental) Abstract: Reinforcement learning (RL) has emerged as an effective approach for enhancing the reasoning capabilities of large language models (LLMs), especially in scenarios where supervised fine-tuning (SFT) falls short due to limited chain-of-thought (CoT) data. Among RL-based post-training methods, group relative advantage estimation, as exemplified by Group Relative Policy Optimization (GRPO), has attracted considerable attention for eliminating the dependency on the value model, thereby simplifying training compared to traditional approaches like Proximal Policy Optimization (PPO). However, we observe that exsiting group relative advantage estimation method still suffers from training inefficiencies, particularly when the estimated advantage approaches zero. To address this limitation, we propose Advantage-Augmented Policy Optimization (AAPO), a novel RL algorithm that optimizes the cross-entropy (CE) loss using advantages enhanced through a margin-based estimation scheme. This approach effectively mitigates the inefficiencies associated with group relative advantage estimation. Experimental results on multiple mathematical reasoning benchmarks demonstrate the superior performance of AAPO. Code is available at this https URL . Comments: Accepted to ACL2026 Main Conference Subjects: Machine Learning (cs.LG) ; Computation and Language (cs.CL) Cite as: arXiv:2505.14264 [cs.LG] (or arXiv:2505.14264v3 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2505.14264 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jian Xiong [ view email ] [v1] Tue, 20 May 2025 12:13:44 UTC (1,687 KB) [v2] Wed, 24 Sep 2025 15:47:49 UTC (1,296 KB) [v3] Tue, 14 Apr 2026 09:06:48 UTC (1,092 KB) Full-text links: Access Paper: View a PDF of the paper titled AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin, by Jian Xiong and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2025-05 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Beyond Surface Forms: Symbolic Edits as a Test for Logical Reasoning with LLMs#799472
• Beyond Surface Forms: Symbolic Edits as a Test for Logical Reasoning with LLMs#798049
• Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework#926044
• Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning#120529
• Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning#668034