Daily Paper Cast

🤗 Upvotes: 120 | cs. CL, cs. SE Authors: Yuling Shi, Jinghan Xu, Kelin Fu, Wenhao Zeng, Shilin He, Lei Zhang, Yue Liu, Zelin Zhao, Terry Yue Zhuo, Jialun Cao, Siyu Ye, Tianyu Liu, Kai Cai, Shing-Chi Cheung, Xiaodong Gu Title: SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring Arxiv: http://arxiv.org/abs/2608.09802v1 Abstract: As AI coding agents take on increasingl...

🤗 Upvotes: 92 | cs. LG Authors: Yijiang Li, Bingyang Wang, Yijun Liang, Yunjie Tian, Di Fu, Nuno Vasconcelos Title: On-Policy Self-Distillation without Any Supervision Arxiv: http://arxiv.org/abs/2608.06296v2 Abstract: On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still rely heavily on external super...

🤗 Upvotes: 68 | cs. SE, cs. AI Authors: Anton Razzhigaev, Andrei Gritsaev, Andrei Kaznacheev, Nikita Dragunov, Roman Yampolskiy, Andrei Kuznetsov Title: Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution Arxiv: http://arxiv.org/abs/2608.08311v2 Abstract: We present Ouroboros, a self-developing agent harness whose tools, prompts, context assembly, and core implementati...

🤗 Upvotes: 37 | cs. AI, cs. LG Authors: Taeil Kim, Kangsan Kim, Sung Ju Hwang Title: Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory Arxiv: http://arxiv.org/abs/2608.07169v1 Abstract: Memory systems have shown promise for improving agent performance, but their potential remains largely unexplored for small language models, which struggle to generate suffici...

🤗 Upvotes: 36 | cs. AI Authors: Junghwan Lim, Joon Son Chung, Sungmin Lee, Wai Ting Cheung, Gihun Cho, Minsu Ha, Sangho Kang, Beomgyu Kim, Dongseok Kim, Jangwoong Kim, Taehyun Kim, Taewhan Kim, Jeesoo Lee, Jeongdoo Lee, Junhyeok Lee, Dongpin Oh, Hyeyeon Cho, Dahye Choi, Jaeheui Her, Hanbin Jung, Changjin Kang, Minjae Kim, Youngrok Kim, Hyukjin Kweon, Hongjoo Lee, Yeongjae Park, Bokki Ryu Title: M...

🤗 Upvotes: 26 | cs. CV, cs. AI Authors: Diandian Zhang, Tingyu Song, Lin Fu, Zheyuan Yang, Yilun Zhao Title: Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains Arxiv: http://arxiv.org/abs/2608.09873v1 Abstract: We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains....

🤗 Upvotes: 25 | cs. CV, cs. AI Authors: Zhijing Zhang, Jinpeng Yu, Xin Song, Bingnan Li, Chuyue Li, Changhui Du, Xiaolin Fang, Jiaming Liu, Ruihua Huang Title: What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems Arxiv: http://arxiv.org/abs/2608.07565v1 Abstract: Conversational assistants increasingly recommend follow-up edits to help users continue a...

🤗 Upvotes: 33 | cs. CL, cs. LG Authors: Kejian Zhu, Zhuoran Jin, Shangqing Tu, Hongbang Yuan, Yushi Bai, Kang Liu, Juanzi Li, Jun Zhao Title: SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Arxiv: http://arxiv.org/abs/2608.03573v2 Abstract: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enh...

🤗 Upvotes: 29 | cs. CV Authors: Kejian Zhu, Zhuoran Jin, Dongqi Huang, Hongbang Yuan, Yupu Hao, Kang Liu, Jun Zhao Title: Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning Arxiv: http://arxiv.org/abs/2608.03571v2 Abstract: Recent works train agents by constructing large-scale multimodal environment pools. However, we find that simply in...

🤗 Upvotes: 22 | cs. CV Authors: Zongchuang Zhao, Xin Zhou, Tianyang Xu, Zhengyang Sun, Kaixuan Zhou, Honglin Li, Dingkang Liang, Xiang Bai Title: SimWAM: A Simple World Action Model for End-to-End Autonomous Driving Arxiv: http://arxiv.org/abs/2608.07468v1 Abstract: World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but exi...

🤗 Upvotes: 72 | cs. AI, cs. LG Authors: Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Jie Wu, Zhengzhou Cai, Yueqing Sun, Ziang Ye, Linji Hao, Qi Gu, Xunliang Cai, Yongliang Shen, Yujiu Yang Title: AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning Arxiv: http://arxiv.org/abs/2608.05987v1 Abstract: Reinforcement learning (RL) with verifiable rewards constructs trajector...

🤗 Upvotes: 58 | cs. AI, cs. CL, cs. CV Authors: Qiushi Sun, Kanzhi Cheng, Yian Wang, Bowen Yang, Hang Yan, Liheng Chen, Fangzhi Xu, Zichen Ding, Nuo Chen, Jialin Cao, Xingdong Gong, Zehao Li, Kaiming Jin, Xinfeng Yuan, Zhoumianze Liu, Jingyang Gong, Zhangyue Yin, Jiahui Gao, Zhiyong Wu, Tianbao Xie, Jianbing Zhang, Ben Kao, Lingpeng Kong Title: OSReward: Instituting Standardized Evaluation for Cr...

🤗 Upvotes: 52 | cs. LG, cs. SD, q-bio. NC Authors: Ilia Semenkov, Daria Kleeva, Ivan Dakhtin, Zarina Maksudova, Alex Ossadtchi Title: Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval Arxiv: http://arxiv.org/abs/2608.01481v1 Abstract: Short segments of perceived speech can be retrieved from non-invasive magnetoencephalographic (MEG) re...

🤗 Upvotes: 50 | cs. AI, cs. CV Authors: Chunchao Guo, Jinpeng Li, Yang Li, Zilong Huang Title: WorldClaw: Agentic 3D Open-World Generation at Scale Arxiv: http://arxiv.org/abs/2608.05248v1 Abstract: Generating large-scale, freely explorable 3D worlds from open-ended text remains challenging because a system must jointly maintain global spatial coherence, rich local content, and explicit assets su...

🤗 Upvotes: 31 | cs. CV Authors: Qifeng Zhang, Kaixiang Huang, Heng Dong, Huang Fang, Junting Chen, Junjie Zhu, Yonghang Chen, Zhiyu Zhang, Wei Li Title: GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Arxiv: http://arxiv.org/abs/2608.05747v1 Abstract: Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or f...

🤗 Upvotes: 30 | cs. AI Authors: Zishan Xu, Zhiyuan Yao, Yuxin Chen, Yifu Guo, Zhengxi Lu, Yuquan Lu, Jinyang Huang, Yan Xu, Yasheng Wang, Weinan Zhang, Xingshan Zeng, Weiwen Liu Title: EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning Arxiv: http://arxiv.org/abs/2608.06197v1 Abstract: Training large language model agents for long-horizon tool use ty...

🤗 Upvotes: 26 | cs. CV Authors: Yifan Shen, Jian Xu, Boyi Li, Yuner Zhang, Tianjiao Yu, Bingxuan Li, Houze Yang, Rushi Wang, Xu Cao Title: ChronoVision: Temporal Reasoning via Latent State Reconstruction Arxiv: http://arxiv.org/abs/2608.05631v1 Abstract: Multimodal large language models excel at passive perception but struggle with complex visual cognitive tasks requiring multi-step temporal reas...

🤗 Upvotes: 26 | cs. CV Authors: Zelong Sun, Jun Wang, Kaicheng Yang, Tiancheng Gu, Ziyong Feng, Zhiwu Lu Title: Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval Arxiv: http://arxiv.org/abs/2608.06060v1 Abstract: Unified multimodal retrieval aims to identify candidates that satisfy complex user intent expressed through heterogeneous inputs. Although...

🤗 Upvotes: 55 | cs. AI Authors: Yijun Lu, Rui Ye, Jiajun Wang, Yuwen Du, Tian Jin, Songhua Liu, Siheng Chen Title: ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Arxiv: http://arxiv.org/abs/2608.05102v1 Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answ...

🤗 Upvotes: 46 | cs. CV Authors: Jiahao Zhao, Xiaomin Yu, Zhongxiang Sun, Fengwei Teng, Chengwei Qin, Xiaobin Hu, Jun Xu, Shuicheng Yan Title: ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation Arxiv: http://arxiv.org/abs/2608.04436v1 Abstract: Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require comp...

🤗 Upvotes: 43 | cs. CV, cs. LG, cs. MM Authors: Junlin Han, Shengbang Tong, David Fan, Minghao Chen, Philip Torr, Filippos Kokkinos, Mike Lewis Title: Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Arxiv: http://arxiv.org/abs/2608.05000v1 Abstract: Vision offers a critical axis for advancing foundation models, driving a shift towards na...

🤗 Upvotes: 21 | cs. RO Authors: Ye Wang, Pei Lin, Xiong-Hui Chen, Haoqi Yuan, Zhixuan Liang, Yiyang Huang, Anzhe Chen, Zixing Lei, Jie Zhang, Tao Zhang, Haoyang Li, Tong Zhang, Chenxi Xiao, Ziyuan Jiao, Qin Jin Title: Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data Arxiv: http://arxiv.org/abs/2608.02580v1 Abstract: Learning generalizable robot manipulation policies requires la...

🤗 Upvotes: 89 | cs. AI Authors: Qiming Shi, Yulong Tao, Linbo Jin, Zhaolu Kang, Yibo Dou, Jiawen Zhu, Tianjun Pan, Shaokang Fu, Chengyu Wang, Siyue Li, Yaping Cheng, Di Weng, Chengfu Huo Title: MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations Arxiv: http://arxiv.org/abs/2607.28956v2 Abstract: Large language model agents are increasingly evaluated as autonomo...

🤗 Upvotes: 79 | cs. CV Authors: Yicheng Xiao, Wenxun Dai, Xinran Qin, Lin Song, Maoquan Zhang, Hang Xu, Yukang Chen, Yitong Li, Guohui Zhang, Yuan Zhang, Xuying Zhang, Tommy Zhang, Jianlong Yuan, Peihao Li, Shuai Lu, Siming Fu, Chuyang Zhao, Xin Han, Jie Huang, Wenbo Li, Guoqing Ma, Wei Huang, Xiaojuan Qi, Haoyang Huang, Nan Duan Title: JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Au...

🤗 Upvotes: 74 | cs. CL Authors: Jiajun Liang, Yucheng Liao, Yukang Cao, Jiazhe Wei, Ken Li, Wende Tan, Jiankun Zhang, ZY Cui, Jingkang Yang, Liucheng Guo, Shiqi Yang, B. Yang, Caifeng Shan, Ziwei Liu, Chenyang Si Title: AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling Arxiv: http://arxiv.org/abs/2608.02602v1 Abstract: Language remains an outlier in...