Advantage

Follow this topic Ask about this topic

Recent momentum

emerging

3 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

33 papers

Latest in Advantage

Open your feed →

DistAL: Distance-based Advantage Learning for VLA Fine-Tuning
Sep 16, 2026Reece O'Mahoney, Ioannis HavoutisVision-Language-Action Models Goal-Conditioned Policy
Beyond Embedding Transfer: Component Roles in Grokking Transfer and Stability
Sep 16, 2026Zeyu JiaDissociation Low-Latency Systems
DIA: Denoising Intermediate Advantage for Diffusion Policy Optimization
Sep 10, 2026Arjun Sohal, Yuchi Zhao, Miroslav Bogdanovic +1Diffusion Policies Behavior Cloning
What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents
Sep 7, 2026Chenqian Le, Jiayi Cheng, Qijia He +3Agentic Reinforcement-Learning Framework Group Relative Policy Optimization
Spurious Advantage Hidden in GRPO
Sep 3, 2026Jiamian Wang, Samyadeep Basu, Koustava Goswami +2Group Relative Policy Optimization Advantage
SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation
Aug 10, 2026Jefferson Hernandez, Jaywon Koo, Zilin Xiao +2Group Relative Policy Optimization Advantage
Aggregate in the Advantage, Not the Ratio: A Canonical-Form Analysis of Cooperative Multi-Agent Policy Optimization
Jul 20, 2026Zijian Zhao, Sen LiMulti-Agent Reinforcement Learning Team Formation
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
Jul 16, 2026Weiwen Xu, Jia Liu, Hou Pong Chan +4Reinforcement Learning With Verifiable Reward Verifiable Rewards
TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings
Jul 13, 2026Jingxiang Zhang, Lujia Zhong, Zijie Zhu +2Multimodal Classification Multimodal Embeddings
Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems
Jul 8, 2026Vladislav BeliaevGroup Relative Policy Optimization Flow-Grpo
Evaluation of Population Initialization Methods for Genetic Programming-based Symbolic Regression
Jun 30, 2026Lukas Kammerer, Gabriel Kronberger, Deaglan J. Bartlett +3Symbolic Regression Genetic Algorithms
Personalizing Marketplace Policies with Competing Objectives and Constrained Experiments: Evidence from a Job Marketplace
Jun 29, 2026Yufei Wu, Zhen YanMatching Markets Personalization
Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF
Jun 25, 2026Arnav RajReinforcement Learning From Human Feedback Deep Reinforcement Learning
Mat-Pref: Verifiable-Reward Training Improves Compositional Reasoning in Inorganic Materials
Jun 20, 2026Sarrah R. Mikhail Leung, Taehan Kim, Jeongbin ParkVast Chemical Space Verifiable Rewards
How Should Agents Read Demonstrations? Hierarchical Structure Beats Flat Action Logs
Jun 18, 2026Honjar Xing, Jefferson Lin, Henry LiebermanProcedural Knowledge Advantage
Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
Jun 16, 2026Xi Chu, Yupeng HouBrand Pairs Recommendation
The Illusion of Multi-Agent Advantage
Jun 11, 2026Prathyusha Jwalapuram, Hehai Lin, Chuyuan Li +7Multi-Agent Systems Table Reasoning Datasets
Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output
Jun 9, 2026Guozheng Li, Xiyan Fu, Yiwen GuoReinforcement Learning From Human Feedback Deep Reinforcement Learning
The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs
Jun 5, 2026Yang Zhang, Xiao Fei, Amr Mohamed +6Multilingual Large Language Models Cultural Knowledge
GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards
Jun 3, 2026Tej Deep Pala, Vernon Toh, Soujanya PoriaReinforcement Learning With Verifiable Reward Verifiable Rewards
Dual Advantage Fields
Jun 2, 2026Alexey Zemtsov, Maxim Bobrin, Alexander Nikulin +5Goal-Conditioned Reinforcement Learning Goal-Conditioned Policy
OPD+: Rethinking the Advantage Design for On-Policy Distillation
May 31, 2026Hanyang Zhao, Haoxian Chen, Han Lin +3On-Policy Distillation Rp-Opsd
CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO
May 29, 2026Yang Li, Gongle Xue, Yijia Guo +3Reinforcement Learning With Verifiable Reward Unsupervised On-Policy Self-Distillation
BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning
May 26, 2026Shijin Gong, Erhan Xu, Kai Ye +3Value Functions Verifiable Rewards
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
May 25, 2026Guochao Jiang, Jingyi Song, Guofeng Quan +3Group Relative Policy Optimization Advantage
Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces
May 21, 2026Mario Severino, Manuela Moretto, Robert A. McCutcheon +1Human Brain Networks Riemannian Manifolds
Vector RAG vs LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research
May 18, 2026Theodore O. CochranHievi-Rag Citations
GAGPO: Generalized Advantage Grouped Policy Optimization
May 13, 2026Siyuan Zhu, Chao Yu, Rongxin Yang +4Agentic Reinforcement-Learning Framework Group Relative Policy Optimization
Stabilizing Efficient Reasoning with Step-Level Advantage Selection
Apr 27, 2026Han Wang, Xiaodong Yu, Jialian Wu +4Large Language Model Reasoning LLM Post-Training Methods
Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents
Apr 20, 2026Jiayi Wu, Ruobing Xie, Zeqian Huang +6Group Relative Policy Optimization Search Agents
Revisiting Auxiliary Losses for Conditional Depth Routing: An Empirical Study
Apr 19, 2026Qingwei LinLarge Language Model Decoder Trainability
Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
Sep 29, 2025Shuchen Xue, Chongjian Ge, Shilong Zhang +2Diffusion Language Models Diffusion Policies
Does YOLO26 Truly Offer Advantages Over Its Predecessors for Edge Deployment? A Benchmark Study in Aquaculture
Date pendingRakesh Ranjan, Gajanan S. Kothawade, Kata Sharrer +2Yolov8-Nano Model Yolo26

Sep 16, 2026 · cs.ROJ/K move · Enter open · S save

DistAL: Distance-based Advantage Learning for VLA Fine-Tuning

Reece O'Mahoney, Ioannis Havoutis

Vision-language-action models (VLAs) have trans- formed the field of robotic manipulation in recent years by combining the semantic understanding of LLMs with the precise control of flow-matching policies. Advantage conditioning is a recent technique that iteratively improves VLAs by training a value function on deployment data and using this to train an advantage-conditioned policy. Previous works have only applied simple, low-information success/failure rewards, which leave the value function unable to distinguish states of differing quality beyond how far along the task they appear. Motivated by an exploration of out-of-distribution (OOD) detection methods, we introduce Distance-based Advantage Learning (DistAL), which, by using an embedding space distance as a reward, produces a more informative value function and subsequently a higher downstream task success rate. We validate our method on a series of simulation benchmarks and dexterous bi-manual manipulation tasks on real hardware.

Vision-Language-Action Models Goal-Conditioned Policy Advantage

Open paper Ask about it PDF