Rise

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 27

All topics

RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation
Oct 1, 2026Jingtan Wang, Sirajul Salekin, Young mok Jung +3Mixture-Of-Agents Reward Functions
National University of Singapore · Work done during an internship at Apple · Apple
UpliftMem: Learning Set-Level Uplift for Agent Memory Retrieval
Sep 29, 2026Mengkun Liang, Haoran Qiang, Guannan Liu +1Rise Test Time
MIIT Key Laboratory of Data and Decision Intelligence Beihang University Beijing, China
RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
Sep 28, 2026Dmitrii Kharlapenko, Sergei Bratchikov, Konstantin Korolev +1Modern Text-To-Image Models Violation
White Circle
Probe to Act: Elevating Browser-Use Agent via Active Visual Probing
Sep 27, 2026Keliang Li, Heng Wang, Chen Hu +3Browser Agent Proactive
Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · StepFun
MAGNETAR: Multipath-Guided Spatial Posteriors for Transmitter Pose Inference in the Upper Mid-Band
Sep 17, 2026Haozhe Lei, Ruibin Chen, Yuhan Jiang +3Radio Map Estimation Indoor Localization
NYU WIRELESS, Tandon School of Engineering, New York University, Brooklyn, NY 11201, USA
Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
Sep 14, 2026Mark Russinovich, Blake Bullwinkel, Giorgio Severi +2Large Language Model Safety Strong Large Language Model
Microsoft Azure · Microsoft
The Rise of Verbal Reinforcement Learning
Sep 1, 2026Kshitij Tayal, Arun Sharma, Genta Indra Winata +2Reinforcement Learning With Verifiable Reward Offline Reinforcement Learning
1AI Foundations, Capital One · University of Minnesota, USA
The rise and evolution of a referential code in populations of bee-like agents
Aug 26, 2026Grzegorz ChrupałaEvolutionary Optimization Methods Rise
Reducing Symmetry Increase in Equivariant Neural Networks
Aug 12, 2026Ning Lin, Jiacheng Cen, Anyi Li +2Equivariant Neural Networks Equivariance
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China
FunnelCausalNet: Funnel-aware Joint Conversion-Revenue Uplift for Multi-tier Coupon Allocation
Aug 12, 2026Yu Zhang, Zhihan Wang, Guanlin Chen +2Click-Through Rate Prediction Rise
AMap Alibaba Group, Beijing, China · AMap Alibaba Group · Beijing, China
UpliftBench: Revealing Outcome-Regime and Objective Mismatch in Uplift Evaluation
Aug 2, 2026Binshuang LiRise Heterogeneous Treatment Effects
Independent Researcher USA
Multi-channel Uplift Policy Learning
Jul 30, 2026Changjian Liu, Tianyu Wang, Xiaoxuan Deng +7Rise Learning-Augmented Algorithms
Peking University Beijing, China · Alibaba Group Beijing, China · Beihang University Beijing, China +1
A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models
Jul 13, 2026Rahul Gupta, Abhinav Mohanty, Payal Motwani +8Realistic Threat Model Rise
Amazon Nova Responsible AI · Work done while at Amazon. · Nemesys Insights
CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling
Jul 6, 2026Zuwang He, Shihao Shu, Yuli Qu +8Incentives Rise
Taobao & Tmall Group of Alibaba Beijing, China · Taobao & Tmall Group of Alibaba Hangzhou, Zhejiang, China
YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate
Jun 22, 2026Suyash MishraPareto Frontier Situation Calculus
AI Researcher
RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation
Jun 22, 2026Yuchuan Ding, Linfei Li, Lin Zhang +1Upsampling Feature Pyramid
School of Computer Science and Technology, Tongji University, Shanghai, China
Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System
Jun 20, 2026Nikki Xu, Hien TranReinforcement Learning Control Generative Control Policies
Department of Mathematics, Box 8205, NC State University, Raleigh, NC 27695
Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants
Jun 12, 2026Dipesh Tharu MahatoRise Pareto Frontier
New York University
The Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models
Jun 12, 2026Zachary Nicholas Houghton, Yu Zhou, Dan Pluth +1Linguistics Large Audio Language Models
University of Oregon · Vail Systems, Inc
RISE: Reliable Improvement in Self-Evolving Vision-Language Models
May 20, 2026Chaoran Xu, Yingmao Miao, Pengfei Zhang +3Recent Vision-Language Models Multimodal Reasoning
AMAP, Alibaba Group
RISED: A Pre-Deployment Evaluation Framework for High-Stakes AI Decision-Support Systems, with Application to Healthcare
May 13, 2026Rohith Reddy Bellibatlu, Manpreet Singh, Yash Jajoo +2Clinical Decision Support Pre-Deployment Safety Assessments
Florida International University, Miami, FL, USA. · Boston University, Boston, MA, USA. · New York University, New York, NY, USA. +2
Learning to Bid with Unknown Private Values in Budget-Constrained First-Price Auctions
May 10, 2026Zihao Hu, Yuxiao Wen, Yuan Yao +2First-Price Auctions Learning-Augmented Algorithms
Department of Mathematics, The Hong Kong University of Science and Technology · Department of IEDA, The Hong Kong University of Science and Technology · Stern School of Business, New York University
Budget-Constrained Causal Bandits: Bridging Uplift Modeling and Sequential Decision-Making
Apr 28, 2026Abhirami PillaiAds Treatment Allocation
utdallas
Shift-Up: A Framework for Software Engineering Guardrails in AI-native Software Development -- Initial Findings
Apr 22, 2026Petrus Lipsanen, Liisa Rannikko, François Christophe +3Software Engineering Ai-Native
University of Jyväskylä Jyväskylä, Finland
Verbal tics in frontier language models: A critical review of current releases, research evidence, and public discussion
Apr 21, 2026Shuai Wu, Xue Li, Zhijun Wang +4Frontier Models Rise
Jointly Optimizing Debiased CTR and Uplift for Coupons Marketing: A Unified Causal Framework
Feb 13, 2026Siyun Yang, Shixiao Yang, Jian Wang +6Click-Through Rate Prediction Treatment Allocation
Kuaishou Technology Beijing, China · Beijing Institute of Technology Beijing, China · Independent Researcher Beijing, China
Soft Swing-up: Benchmarking Model-Based Optimal Control for Rigid-Soft Underactuated Systems
Feb 3, 2026Daniele Caradonna, Nikhil Nair, Anup Teejo Mathew +5Soft Robotics Underactuated Dynamics
The BioRobotics Institute, Scuola Superiore Sant’Anna, Pisa, Italy · Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, Pisa, Italy · Department of Cognitive Robotics, Delft University of Technology, 2628 CN Delft, The Netherlands +3

Oct 1, 2026, cs.AIJ/K move · Enter open · S save

RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation

Jingtan Wang, Sirajul Salekin, Young mok Jung, Javier Movellan+2

National University of Singapore · Work done during an internship at Apple · Apple

Mixture-Of-Agents Reward Functions Rubrics Token-Level Supervision Agent Behavior Modeling Rise

Open paper AskPDF arXiv

Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selection strategies often allocate training at the environment level or prioritize local reward-based signals, without explicitly considering relationships between current rollouts across environments for prompt-group selection. Meanwhile, as environments are learned at different rates, all-failure and all-success rollout groups can coexist within a batch, leaving those data without group-relative reward signals. Both challenges highlight limitations of relying solely on scalar rewards in multi-environment RL: they provide limited information about cross-environment relationships and no within-group reward contrast when rewards are identical. This motivates richer textual feedback, such as rubrics describing rollout behaviours, to guide learning. Beyond rubrics' usage as reward, we repurpose rubrics to guide both online data selection and policy supervision. An LLM judge tags each rollout using a predefined rubric vocabulary shared across environments. The resulting profiles guide the selection of data that aligns with the overall behavioural composition of the mixed-environment batch while limiting overlap with already-selected data. Available positive rubrics (describing desired behaviours) provide privileged context for an on-policy self-distillation teacher, supplying additional token-level supervision, while negative rubrics (describing undesired behaviours) guide subsequent rollout generation away from recurring failure modes. Together, these components form RISED. Across model backbones, RISED achieves the highest mean pass rate across environments and ranks first or second in every individual environment. Rubric-based analysis of RISED can further characterize the behavioural changes accompanying these gains.

Momentum

Related topics

Latest papers 27