Ax Hehai Lin, Shilei Cao, Sudong Wang, Haotian Wu, Minzhi Li, Linyi Yang, Juepeng Zheng, Chengwei Qin 4/14/2026

Interactive Learning for LLM Reasoning

Interactive learning approach enabling LLMs to improve reasoning through multi-agent interactions during inference without re-execution.

Ax Yuyang Liu, Chuan Wen, Yihang Hu, Dinesh Jayaraman, Yang Gao 4/14/2026

TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance

Reward learning method deriving progress estimation signals from passive videos for robotics RL tasks without manual reward engineering.

Ax Shaoan Xie, Lingjing Kong, Xiangchen Song, Xinshuai Dong, Guangyi Chen, Eric P. Xing, Kun Zhang 4/14/2026

Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards

RL method for improving reasoning in diffusion-based language models using denoising process rewards instead of outcome-only rewards.

Ax Wenda Xie, Chao Guo, Yanqing Jing. Junle Wang, Yisheng Lv, Fei-Yue Wang 4/14/2026

Plug-and-Play Dramaturge: A Divide-and-Conquer Approach for Iterative Narrative Script Refinement via Collaborative LLM Agents

Multi-agent LLM system for iterative narrative script refinement using divide-and-conquer approach to improve long-form creative content generation.

Ax Pengkun Jiao, Yiming Jin, Jianhui Yang, Chenhe Dong, Zerui Huang, Shaowei Yao, Xiaojiang Zhou, Dan Ou, Haihong Tang 4/14/2026

SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance

RL framework for e-commerce search relevance using stepwise reward optimization to improve LLM-based query-product matching beyond SFT/DPO limitations.

Ax Weihua Cheng, Junming Liu, Yifei Sun, Botian Shi, W Yirong Chen, Ding Wang 4/14/2026

MGA: Memory-Driven GUI Agent for Observation-Centric Interaction

MGA memory-driven GUI agent reduces context overload and architectural redundancy by managing sequential trajectory history for improved long-horizon end-to-end automation.

Ax Junze Ye, Daniel Tawfik, Alex J. Goodell, Nikhil V. Kotha, Mark K. Buyyounouski, Mohsen Bayati 4/14/2026

Scalable Stewardship of an LLM-Assisted Clinical Benchmark with Physician Oversight

Audits MedCalc-Bench clinical labels using physician-in-the-loop stewardship to assess reliability of LLM-synthesized reference labels in ML benchmarks.

Ax Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu 4/14/2026

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration

PRISM framework disentangles SFT and RL training data via gradient concentration to diagnose learning needs and optimize data allocation for LLM agent training.

Ax Keyu Li, Junhao Shi, Yang Xiao, Mohan Jiang, Jie Sun, Yunze Wu, Dayuan Fu, Shijie Xia, Xiaojie Cai, Tianze Xu, Weiye Si, Wenjie Li, Dequan Wang, Pengfei Liu 4/14/2026

AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts

AgencyBench evaluates LLM-based autonomous agents on long-horizon real-world scenarios with 1M-token context windows, enabling scalable automated evaluation without human-in-the-loop.

Ax Mengxuan Wang, Yuxin Chen, Gang Xu, Tao He, Hongjie Jiang, Ming Li 4/14/2026

Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility

Risk Awareness Injection method calibrates vision-language models against multimodal jailbreak attacks without fine-tuning or token manipulation, preserving model utility.

Ax Jinbiao Wei, Yilun Zhao, Kangqi Ni, Arman Cohan 4/14/2026

ANCHOR: Branch-Point Data Generation for GUI Agents

ANCHOR framework generates high-quality synthetic training data for GUI agents by trajectory expansion from seed demonstrations to create diverse, goal-consistent interaction data.

Ax Alisa Vinogradova, Vlad Vinogradov, Luba Greenwood, Ilya Yasny, Dmitry Kobyzev, Shoman Kasbekar, Kong Nguyen, Dmitrii Radkevich, Roman Doronin, Andrey Doronichev 4/14/2026

Hunt Globally: Wide Search AI Agents for Drug Asset Scouting in Investing, Business Development, and Competitive Intelligence

AI agent system for pharmaceutical drug asset scouting across global non-English channels to identify novel drug development opportunities via multi-source intelligence.

Ax Jiahao Huang, Fengyan Lin, Xuechao Yang, Chen Feng, Kexin Zhu, Xu Yang, Zhide Chen 4/14/2026

Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy

Nano-EmoX proposes three-level cognitive hierarchy (perception, understanding, interaction) for unified multimodal emotional intelligence in language models with empathy capabilities.

Ax Boqin Yuan, Yue Su, Kun Yao 4/14/2026

Diagnosing Retrieval vs. Utilization Bottlenecks in LLM Agent Memory

Diagnostic framework for LLM agent memory systems comparing write strategies, retrieval methods, and utilization behavior to identify performance bottlenecks across memory components.

Ax Binxia Xu, Xiaoliang Luo, Luke Dickens, Robert M. Mok 4/14/2026

Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment

Analyzes whether AI systems fail similarly to humans using error alignment metrics on out-of-distribution data to assess cognitive similarity and decision-making strategies.

Ax Luca Deck, Simeon Allmendinger, Lucas M\"uller, Niklas K\"uhl 4/14/2026

Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-Agent AI

NormCoRe framework studies how norms emerge in multi-agent AI systems through deliberation and negotiation using replication-by-translation methodology for fairness-sensitive domains.

Ax Wenxuan Zhang, Lemeng Wu, Changsheng Zhao, Ernie Chang, Mingchen Zhuge, Zechun Liu, Andy Su, Hanxian Huang, Jun Chen, Chong Zhou, Raghuraman Krishnamoorthi, Vikas Chandra, Mohamed Elhoseiny, Wei Wen 4/14/2026

dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models

dTRPO algorithm reduces trajectory probability calculation costs for policy optimization of diffusion-based LLMs, enabling scaled offline RL training for preference alignment.

Ax Nicolas Martorell, Bruno Bianchi 4/14/2026

Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation

Method for tracking internal states of LLMs across conversations using self-report-inspired techniques for safety, interpretability, and model welfare without white-box compression.

Ax Diego Calvanese, Angelo Casciani, Giuseppe De Giacomo, Marlon Dumas, Fabiana Fournier, Timotheus Kampik, Emanuele La Malfa, Lior Limonad, Andrea Marrella, Andreas Metzger, Marco Montali, Daniel Amyot, Peter Fettke, Artem Polyvyanyy, Stefanie Rinderle-Ma, Sebastian Sardi\~na, Niek Tax, Barbara Weber 4/14/2026

Agentic Business Process Management: A Research Manifesto

Manifesto proposing Agentic Business Process Management (APM) framework extending BPM to govern autonomous agents executing organizational processes with agent-oriented abstractions.

Ax Lijing Luo, Yiben Luo, Alexey Gorbatovski, Sergey Kovalchuk, Xiaodan Liang 4/14/2026

From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments

Large-scale empirical study analyzing 2,000+ publications on reinforcement learning environments, proposing a taxonomy of RL environment evolution and technological trends.

Ax Silvia Rossi, Diletta Huyskes, Mackenzie Jorgensen 4/14/2026

Resisting Humanization: Ethical Front-End Design Choices in AI for Sensitive Contexts

Examines ethical front-end design choices in conversational AI systems, focusing on user interaction and representation rather than backend algorithmic issues.

Ax Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo, Rishi Hazra, Michael Kuchnik, Bassel Al Omari, Thomas Simon Foster, Anton Protopopov, Jean-Christophe Gagnon-Audet, Ishita Mediratta, Kelvin Niu, Michael Shvartsman, Alisia Lupidi, Alexis Audran-Reiss, Parth Pathak, Tatiana Shavrina, Despoina Magka, Hela Momand, Derek Dunfield, Nicola Cancedda, Pontus Stenetorp, Carole-Jean Wu, Jakob Nicolaus Foerster, Yoram Bachrach, Martin Josifoski 4/14/2026

AIRA_2: Overcoming Bottlenecks in AI Research Agents

AIRA_2 addresses three bottlenecks in AI research agents: synchronous GPU execution, generalization gaps, and fixed LLM operator limitations through improved architectural design.

Ax Zhenyuan Zhao, Yu Xing, Tianyang Xue, Lingxin Cao, Xin Yan, Lin Lu 4/14/2026

AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Design

AutoMS is a multi-agent neuro-symbolic framework using LLMs as semantic navigators for evolutionary search in inverse microstructure design, addressing topology optimization challenges.

Ax Hanrong Zhang, Shicheng Fan, Henry Peng Zou, Yankai Chen, Zhenting Wang, Jiayu Zhou, Chengze Li, Wei-Chieh Huang, Yifei Yao, Kening Zheng, Xue Liu, Xiaoxiao Li, Philip S. Yu 4/14/2026

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

CoEvoSkills framework enables LLM agents to self-evolve structured multi-file skill artifacts through co-evolutionary verification without manual authoring.

Ax Ying Yao 4/14/2026

RL-Driven Sustainable Land-Use Allocation for the Lake Malawi Basin

Deep RL framework optimizes land-use allocation in Lake Malawi Basin to maximize ecosystem service value with ecological constraints.

Ax Anushree Sinha, Srivaths Ranganathan, Debanshu Das, Abhishek Dharmaratnakar 4/14/2026

Beyond Fluency: Toward Reliable Trajectories in Agentic IR

Position paper on failure modes in agentic IR systems, analyzing error cascades in multi-step reason-act-observe workflows despite linguistic fluency.

Ax Hieu Le, Mostafa Ibrahim, Oguz Bedir, Jian Tao, Sabit Ekin 4/14/2026

Learning to Focus: CSI-Free Hierarchical MARL for Reconfigurable Reflectors

Hierarchical multi-agent RL framework for reconfigurable intelligent surfaces removes need for channel state information estimation.

Ax Chengyi Yang, Pengzhen Li, Jiayin Qi, Aimin Zhou, Ji Wu, Ji Liu 4/14/2026

SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation

SCMAPR uses self-correcting multi-agent prompt refinement to improve text-to-video generation in complex scenarios with ambiguous prompts.

Ax Qing Guo, Xinhang Li, Junyu Chen, Zheng Guo, Shengzhe Xu, Lin Zhang, Lei Li 4/14/2026

CuraLight: Debate-Guided Data Curation for LLM-Centered Traffic Signal Control

CuraLight combines LLM-centered control with debate-guided data curation for interpretable and generalizable traffic signal control systems.

Ax Yunbo Long, Yuhan Liu, Liming Xu 4/14/2026

EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration

EmoMAS uses Bayesian multi-agent framework with small language models for emotionally-aware negotiation in privacy-sensitive edge deployments.

Ax Jianfei Wu, Zhichun Wang, Zhensheng Wang, Zhiyu He 4/14/2026

EVGeoQA: Benchmarking LLMs on Dynamic, Multi-Objective Geo-Spatial Exploration

EVGeoQA benchmark evaluates LLM reasoning on dynamic geo-spatial exploration with multi-objective planning and compound constraints.

Ax Yiwen Wang, Gregory Sinenka, Xhuliano Brace 4/14/2026

Rhizome OS-1: Rhizome's Semi-Autonomous Operating System for Small Molecule Drug Discovery

Rhizome OS-1 is a semi-autonomous operating system deploying multi-modal AI agents as computational and medicinal chemists for drug discovery.

Ax David Gringras 4/14/2026

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures

Pre-registered study demonstrating AI safety measures can cause harmful outputs in medical domains, with contextual prompting changing model behavior.

Ax Xinshun Feng, Xinhao Song, Lijun Li, Gongshen Liu, Jing Shao 4/14/2026

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents

SEARL framework enables self-evolving agents through joint optimization of policy and tool graph memory, reducing reliance on large-scale LLMs.

Ax Mohamed Elfeki, Tu Trinh, Kelvin Luu, Guangze Luo, Nathan Hunt, Ernesto Montoya, Nandan Marwaha, Yannis He, Charles Wang, Fernando Crabedo, Alessa Castilo, Bing Liu 4/14/2026

HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?

HiL-Bench evaluates whether coding agents know when to request help with incomplete specifications, exposing judgment gaps in frontier models.

Ax Gonzalo Ballestero, Hadi Hosseini, Samarth Khanna, Ran I. Shorrer 4/14/2026

Strategic Algorithmic Monoculture: Experimental Evidence from Coordination Games

Empirical study of how LLM agents coordinate in multi-agent games, distinguishing baseline action similarity from strategic algorithmic monoculture.

Ax Paul Geertsema, Helen Lu 4/14/2026

AXIL: Exact Instance Attribution for Gradient Boosting

AXIL derives exact instance attribution method for gradient boosting machines, expressing predictions as weighted sums of training targets.

Ax Minsik Oh, Jiwei Li, Guoyin Wang 4/14/2026

Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings

Proposes contrastive learning method for dialogue sentence embeddings using token-level template annotations instead of utterance-level labels.

Ax Sameera Horawalavithana, Sai Munikoti, Ian Stewart, Henry Kvinge, Karl Pazdernik 4/14/2026

SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions

SciTune framework aligns LLMs with scientific domain knowledge through instruction fine-tuning on multimodal scientific publication data.

Ax Lai Wei, Xiaozhe Li, Zihao Jiang, Weiran Huang, Lichao Sun 4/14/2026

MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets

MM-LIMA demonstrates multimodal LLM fine-tuning achieves strong results with only 200 high-quality instruction examples, reducing data requirements.

Ax Hao Li, Xiao-Hu Zhou, Shu-Hai Li, Mei-Jiang Gui, Xiao-Liang Xie, Shi-Qi Liu, Shuang-Yi Wang, Zhen-Qiu Feng, Zeng-Guang Hou 4/14/2026

CROP: Conservative Reward for Model-based Offline Policy Optimization

Proposes CROP, a model-based offline reinforcement learning method addressing distribution shift through conservative reward estimation.

Ax Hengran Zhang, Keping Bi, Jiafeng Guo, Xueqi Cheng 4/14/2026

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs

Framework using LLMs with philosophical relevance concepts to improve utility-based result ranking in retrieval-augmented generation systems.

Ax Lionel Z. Wang, Ka Chung Ng, Yiming Ma, Wenqi Fan 4/14/2026

MegaFake: A Theory-Driven Dataset of Fake News Generated by Large Language Models

MegaFake dataset of LLM-generated fake news for studying mechanisms of misinformation generation and detection methods.

Ax Avinash Maurya, Jie Ye, M. Mustafa Rafique, Franck Cappello, Bogdan Nicolae 4/14/2026

Deep Optimizer States: Towards Scalable Training of Transformer Models Using Interleaved Offloading

Deep Optimizer States method enables scalable training of transformer models using interleaved offloading to overcome memory constraints.

Ax Qingyang Mao, Qi Liu, Zhi Li, Mingyue Cheng, Zheng Zhang, Rui Li 4/14/2026

PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables

PoTable framework improves table reasoning in LLMs using plan-then-execute reasoning stages for systematic thinking.

Ax Charlie F. Ruan, Yucheng Qin, Akaash R. Parthasarathy, Xun Zhou, Ruihang Lai, Hongyi Jin, Yixin Dong, Bohan Hou, Meng-Shiun Yu, Yiyan Zhai, Sudeep Agarwal, Hangrui Cao, Siyuan Feng, Tianqi Chen 4/14/2026

WebLLM: A High-Performance In-Browser LLM Inference Engine

WebLLM inference engine enabling high-performance LLM execution directly in web browsers for on-device deployment without server GPUs.

Ax Ting Zhou, Daoyuan Chen, Qirui Jiao, Bolin Ding, Yaliang Li, Ying Shen 4/14/2026

HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks

HumanVBench benchmark for evaluating human-centric video understanding in multimodal large language models with 16 fine-grained tasks.

Ax Stephane Hatgis-Kessell, W. Bradley Knox, Serena Booth, Peter Stone 4/14/2026

Influencing Humans to Conform to Preference Models for RLHF

Three human studies examining whether humans can be influenced to conform to preference models used in RLHF algorithms for LLMs.

Ax Fausto Mauricio Lagos Suarez, Akshit Saradagi, Vidya Sumathy, Shruti Kotpaliwar, George Nikolakopoulos 4/14/2026

Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotor

Novel curriculum learning approach for sample-efficient reinforcement learning applied to quadrotor stabilization control.

Ax Wanli Ma, Oktay Karakus, Paul L. Rosin 4/14/2026

Integrating Semi-Supervised and Active Learning for Semantic Segmentation

Combines semi-supervised and active learning for semantic segmentation to reduce manual annotation costs and improve model performance.