Daily Paper Cast

🤗 Upvotes: 32 | cs. AI, cs. LG Authors: Changdae Oh, Qi Zeng, Qi Qi, Andrey Zhmoginov, Deren Lei, Yun He, Hoang Phan, Hangoo Kang, Azalia Mirhoseini, Sharon Li Title: Sharpening Tax in Post-Training Arxiv: http://arxiv.org/abs/2610.01509v1 Abstract: An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors...

🤗 Upvotes: 32 | cs. CL Authors: Chenguang Wang, Ming Li, Chengrui Fan, Jianpeng Chen, Han Chen, Tianyi Zhou, Dawei Zhou Title: A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review Arxiv: http://arxiv.org/abs/2609.39027v1 Abstract: AI reviewers can assign different judgments to manuscripts that report the same science in different wording, potenti...

🤗 Upvotes: 29 | cs. CV Authors: Zheng-Hui Huang, Guixu Lin, Yu-Ju Tsai, Jian-Kai Zhu, Fengbo Lan, Yu-Lun Liu, Yung-Yu Chuang, Kaipeng Zhang, Zhixiang Wang Title: ROWBench: Do Video Models Render What the Program Specifies? Arxiv: http://arxiv.org/abs/2610.02205v1 Abstract: Programmable world models separate executable dynamics from visual generation, offering a promising foundation for next-gener...

🤗 Upvotes: 27 | cs. CV Authors: Cheng Yang, Yifan Wu, Yutao Huang, Zhaohua Zhang, Beiduo Chen, Muxi Chen, Chenchen Zhao, Hexuan Deng, Haolin Yang, Geyuan Zhu, Sa Zhu, Jianhuan Zhuo, Qiuyong Xiao, Jianhao Ruan, Yiran Peng, Jiayi Zhang, Tian Ye, Xinlei Yu, Tianwen Jiang, Jihong Zhang, Yuyu Luo Title: AutoGUIWorld: Image Generators as Visual World Models for GUI Agent Arxiv: http://arxiv.org/abs/261...

🤗 Upvotes: 134 | cs. LG Authors: Hao Li, MeiJia Chen, Weijie Ren, Donghan Li, Zijun Tian, Jingchun Huang, Naibo Wang Title: The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Arxiv: http://arxiv.org/abs/2609.36484v1 Abstract: On-policy distillation (OPD) trains a student to match the teacher's next-token distributions on the...

🤗 Upvotes: 120 | cs. AI, cs. CV Authors: Fang Wu, Da Xing, Yanjie Huang, Junxi Wang, Ji Wang, Hejia Geng, Guancheng Wan, Bowen Zuo, Xiaomin Li, Shixiang Tang, Xinyu Xiang, Zehong Wang, Shiyi Du, Peng Xia, Shuangjia Zheng, Yining Hong, Li Erran Li, Jure Leskovec, Yejin Choi Title: UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Arxiv: http://arxiv.or...

🤗 Upvotes: 68 | cs. CL, cs. AI, cs. LG Authors: Meijia Chen, Hao Li, Zheng Lu, Hongshan Lin, Junbai Tian, Yichen Liu, Zijun Tian, Yufan Zou, Shuhan Sun, Hanxin Chen, Zeyu Zhang, Weizhi Du, Yueting Li, Tianyu Shi, Alaa Khamis Title: False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Arxiv: http://arxiv.org/abs/2609.39102v1 Abstract: Self-evolving search agents bu...

🤗 Upvotes: 64 | cs. AI Authors: Hongjin Qian, Chaofan Li, Kun Luo, Wenqing Wei, Jianlyu Chen, Shuqi Lu, Yuyang Hu, Hongwang Xiao, Hui Wang, Chaozhuo Li, Qiwei Ye, Zhicheng Dou, Defu Lian, Zheng Liu Title: AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Arxiv: http://arxiv.org/abs/2609.38288v1 Abstract: We present AREX-2, an effort to advance the self-improving capabi...

🤗 Upvotes: 60 | cs. AI Authors: Ziyan Jiang, Jingbo Yang, Jiabao Ji, Yujian Liu, Qiucheng Wu, Tommi Jaakkola, Yang Zhang, Shiyu Chang Title: WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents Arxiv: http://arxiv.org/abs/2609.40325v1 Abstract: As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for ide...

🤗 Upvotes: 57 | cs. CL, cs. AI, cs. MA Authors: Minki Kang, Ryo Hachiuma, Shaokun Zhang, Subhashree Radhakrishnan, Yonggan Fu, Jindong Jiang, Mingjie Liu, Ehsan Hosseini-Asl, Yi Dong, Yu-Chiang Frank Wang, Byung-Kwan Lee Title: Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents Arxiv: http://arxiv.org/abs/2609.39982v1 Abstract: Terminal agents act through stochastic model...

🤗 Upvotes: 41 | cs. AI, cs. CL, cs. LG Authors: Cheng Qian, Kunlun Zhu, Beibin Li, Zhenhailong Wang, Heng Ji Title: Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI Arxiv: http://arxiv.org/abs/2609.38143v1 Abstract: Agent performance depends on both reasoning ability and the environment in which it acts. We study test-time AI-for-AI, asking how a Builder can learn to construct bet...

🤗 Upvotes: 37 | cs. CL Authors: Yuhan Guo, Jinming Liu, Liang Xu, Ziqiang Li, Jianguo Huang, Zhicheng Wang, Hu Zhu, Qiuyu Chen, Yuntao Wei, Xin Jin, Wenjun Zeng Title: EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making Arxiv: http://arxiv.org/abs/2609.38334v1 Abstract: Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet tra...

🤗 Upvotes: 29 | cs. AI Authors: Tianxiang Gao, Jinzhe Li, Zhiyuan Li, Yi Chang, Yuan Wu Title: More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models Arxiv: http://arxiv.org/abs/2609.38827v1 Abstract: Direct-decision models turn text into low-latency structured labels and scores, making them attractive for classification and automatic evaluation. Yet reliability requ...

🤗 Upvotes: 254 | cs. AI, cs. CL, cs. GT, cs. MA, cs. NE Authors: EverMind AI Title: Raven: The Harness of Harnesses for Composable Agentic Intelligence Arxiv: http://arxiv.org/abs/2609.33439v1 Abstract: As large language models advance, AI agents are moving beyond isolated, domain-specific tasks toward long-horizon, cross-domain workflows. This transition exposes two challenges: increasing harnes...

🤗 Upvotes: 189 | cs. CV Authors: Haoyu Zhao, Zihao Zhang, Xudong Wang, Jiaxi Gu, Zuxuan Wu, Yu-Gang Jiang, Shuicheng Yan Title: MaLiang-Harness: A Programmable Path to Image and Video Generation Arxiv: http://arxiv.org/abs/2609.34309v1 Abstract: Executable programs offer explicit control over how images and videos are constructed, but generating runnable code is only the beginning of visual creat...

🤗 Upvotes: 88 | cs. CV, cs. RO Authors: Zhen Wang, Changpeng Wang, Zhe Liu, Zhangyang Qi, Yuxiang Lu, Zimo Zeng, Donglian Qi, Xi Chen Title: PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation Arxiv: http://arxiv.org/abs/2609.34759v1 Abstract: Recent vision-language models (VLMs) have advanced vision-and-language navigation (VLN), enabling models to predict navigation actions from...

🤗 Upvotes: 57 | cs. CL Authors: Yanlin Li, Mingyang Hao, Shengqiong Wu, Hao Fei, Mong-Li Lee, Wynne Hsu Title: Omni-IO Skills: Harnessing Your Agent Omni-Native Arxiv: http://arxiv.org/abs/2609.31847v1 Abstract: General-purpose agents can plan, reason, and act over long horizons, yet their production capabilities remain fragmented across text, images, audio, video, documents, 3D assets, and code....

🤗 Upvotes: 55 | cs. CV, cs. RO Authors: Renping Zhou, Zanlin Ni, Zihao Fan, Guohao Fu, Zeyu Liu, Hao Shi, Jie Zhang, Chi Bene Chen, Yang Yue, Xueyang Fu, Gao Huang Title: What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling Arxiv: http://arxiv.org/abs/2609.34981v2 Abstract: World action models (WAMs) predict the future alongside actions during training. Due t...

🤗 Upvotes: 52 | eess. AS, cs. SD Authors: Yang Xiao, Vidhyasaharan Sethu, Eun-Jung Holden, Ting Dang Title: VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models Arxiv: http://arxiv.org/abs/2609.32607v1 Abstract: Spoken conversational systems must recover information from prior interactions (i.e., memory), yet relevant information in speech extends beyond what was said to who said...

🤗 Upvotes: 45 | cs. CV Authors: Xuehai Bai, Zhenchen Tang, Yang Shi, Dianyi Wang, Tengfei Liu, Wanshun Su, Xuanyu Zhu, Ruohui Wang, Haiwen Diao, Haotian Wang, Xiaoling Gu, Yuanxing Zhang Title: Think Before You Score: Thinking Reward Model for Visual Generation Arxiv: http://arxiv.org/abs/2609.37372v1 Abstract: Visual reward models are essential for evaluating and improving visual generation mode...

🤗 Upvotes: 43 | cs. RO, cs. LG Authors: Haojian Huang, Zexi Li, Junhao Guo, Yehang Zhang, Wenxuan Peng, Bohan Zhou, Weilin Ruan, Leyi Wu, Chenxu Wang, Jianchong Su, Binghui Xie, Wosong Chen, Yingjie Xu, Tianhao Zhou, Suzeyu Chen, Pukun Zhao, Jiaqi He, Xinyi Li, Runze Li, Peiran Dong, Shaoxiang Dang, Jing Huang, Yingbing Chen, Yifan Chang, Tianyi Zhang, Shiyuan Deng, Haozhi Wang, Yangkai Wei, Wenq...

🤗 Upvotes: 41 | cs. CV, cs. AI, cs. CL, cs. IR, cs. LG Authors: Hui Ren, Lei Fan, Henry Pao, Han Guo, Zeeshan Zia, Ying Chen, Alexander Schwing, Gang Hua Title: Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies Arxiv: http://arxiv.org/abs/2609.38155v1 Abstract: Answering questions about long videos often requires connecting events involving the same objects across...

🤗 Upvotes: 37 | cs. AI Authors: Miteto Wei, Xiaohan Wang, Zehao Chen, Jiajun Chai, Sichao Liu, Li Wang, Haoyuan Xu, Zhaoyu Hu, Wei Lin, Guojun Yin Title: SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation Arxiv: http://arxiv.org/abs/2609.36601v1 Abstract: On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectorie...

🤗 Upvotes: 58 | cs. LG Authors: Xin Li, Hao Jiang, Xin Gao, Annan Wang, Yuchen Xie, Jinghao Guo, Xingwei Qu, Yichi Zhang, Chau Yuen Title: Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation Arxiv: http://arxiv.org/abs/2609.35347v1 Abstract: Reinforcement learning can turn one language model into several specialists, each excellent at a single skill such as mathemati...

🤗 Upvotes: 56 | eess. AS, cs. LG, cs. SD Authors: Ruibin Yuan, Jiahao Pan, Junyan Jiang, Zhiyue Wu, Ziya Zhou, Jiankai Sun, Yizhi Li, Ge Zhang, Yicheng Gu, Zeyue Tian, Junyu Dai, Hanfeng Lin, Kai Li, Shangda Wu, Xuanjie Liu, Jiaming Wang, Zihan Liu, Yue Wang, Yinghao Ma, Hanzhi Yin, Kangrui Chen, Xinyue Zhang, Ziyang Ma, Mengqi Liao, Hejia Zhao, Guowei Huang, Chao Yan, Lei Ke, Jianwei Yu, Bei Liu...