…Economic Perspective on Optimal Budget Allocation for LLMs Published on Jun 2 Submitted by XuWan on Jun 5 Peking University Authors: Xu Wan , , , , , , Abstract Inference-time scaling is enhanced through constrained optimization…
…adapt a prior method shift agents toward method-guided exploration . The scaffolded agent autonomously composes -- without human design input -- a data-selection policy that outperforms strong published baselines at one-tenth their…
…Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding Published on May 28 Submitted by 黄佳诺 on Jun 2 #3 Paper of the day Shanghai Jiao Tong University Authors: Jianuo Huang , , , , , Abstract…
…Geometric Origin, Systemic Impact, and UFP4 Recipe Published on Jun 18 Submitted by Qian Zhao on Jun 19 inclusionAI Authors: Qian Zhao , , Changxin Tian , , , , , , , , , Abstract Uniform 4-bit training with RHT-based…
…A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning Published on May 13 Submitted by taesiri on May 14 Authors: , , , , , , , , Abstract Interactive LLM agents suffer from delayed environmental perception and…
…Test-Time Scaling for Streaming Video Generation Published on May 6 Submitted by Mengqi Huang on May 7 #2 Paper of the day FrameX-AI Authors: , Shaojin Wu , , , , , Abstract Stream-T1 enables…
Papers arxiv:2606.18531 When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning? Published on Jun 16 Submitted by Xuanfei Ren on Jun 18 University of Wisconsin - Madison Authors: Xuanfei Ren…
…Dynamic Cross-Modal Coordination for Visual Reasoning Published on Jun 6 Submitted by Hangui Lin on Jun 11 Authors: Hangui Lin , , , , , , , , Abstract Dynamic cross-modal coordination is integrated into reinforcement learning with…
…Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts Published on Jun 8 Submitted by Sajib Acharjee Dip on Jun 10 University of Illinois at Urbana-Champaign Authors: , , , , , , Abstract Researchers…
Papers arxiv:2605.14354 LLM-based Detection of Manipulative Political Narratives Published on May 14 Submitted by Sinclair Schneider on May 15 NLP Research Group UniBW Authors: Sinclair Schneider , , Abstract A computational…