arXiv:2609.29444v1 Announce Type: new Abstract: Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limitations: role coupling, where one policy must handle planning, evidence use, and synthesis; and context accumulation, where growing search histories introduce noise and obscure useful information. To address these issues, we propose IterSynth, a role-decoupled and summary-based paradigm that alternates between a Planner for identifying information needs and a Synthesizer for integrating evidence into an evolving summary state. Thi
arXiv:2609.29145v1 Announce Type: new Abstract: A generative search answer can cite a supported passage yet omit a source relationship that changes its interpretation. We specify a claim-gated audit of the query-source-answer tuple. An omission is resolved only when relationship evidence, answer adoption, materiality, and disclosure are all observed; incomplete evidence remains unresolved rather than being treated as independence. The specification separates this endpoint from citation support and review priority, and binds decisions to versioned evidence spans. A reference checker makes the record contract executable. On an exhaustive synthe
arXiv:2609.28809v1 Announce Type: new Abstract: Mechanistic interpretability seeks to make verifiable statements about the internal behavior of large language models (LLMs). Many interpretability techniques struggle to scale with the increasing size and depth of architectures. Our solution to this is to introduce smaller models with structures that lend themselves to interpretability. In this work, we introduce the Stream Recursion Model (SRM), a modification of the Hierarchical Reasoning Model (HRM) designed to expose internal computational structure while remaining scalable. SRM organizes computation into multiple interacting latent streams
arXiv:2609.28832v1 Announce Type: new Abstract: Reconstruction-based unsupervised learning can fail in two opposing ways: a model may reconstruct anomalies too accurately or discard valid nominal variation. Using the Pursuit of Subspaces hypothesis, we characterize these failures through the meet, union, and join geometries induced by the nominal components. Excess learned range produces join blindness, while insufficient capacity produces meet preference and loss of nominal fidelity. We show that the compact nominal union is optimal among nominal faithful ranges and generally requires a nonlinear reconstruction map. Based on this geometry, w
arXiv:2609.28845v1 Announce Type: new Abstract: On-policy distillation (OPD) corrects a student on the responses it writes, but its signal is the teacher's next-token distribution: it tells the student what the teacher says but misses how it thinks. Latent supervision promises the missing part by aligning the student's latent states to the teacher's. Recent methods such as OPRD bring this signal into on-policy distillation. However, we observe two failures of this recipe when distilling Qwen3-4B and Qwen3-8B into Qwen3-1.7B-Base. Early gain, late collapse: latent supervision alone lifts MATH-500 accuracy from 25 to 46 in 10 steps, but subsequ
arXiv:2609.28868v1 Announce Type: new Abstract: Neural fields for scientific tomography are optimized from 2D images, but the actual quantity of interest is often a latent 3D physical field. Because the forward map is many-to-one, low 2D image error need not certify a correct 3D field. Moreover, the latent field is not directly supervised during training, and its error cannot be evaluated against truth at deployment. We develop CoroNeRF to jointly optimize 3D electron density and temperature fields directly from multiview, multiline intensities through a differentiable atomic-emission renderer. Using solar coronal tomography as a controlled t
arXiv:2609.28935v1 Announce Type: new Abstract: Vibrational spectral prediction can become inaccurate when localized stereoelectronic environments perturb intermediate response states and high-risk response units dominate characteristic spectral fingerprints, making prediction across external chemical space difficult. SO(3) Equivariant Neural Kalman Networks (SENK) form a response-state cascade that combines an equivariant transformer backbone for Hessian, dipole-derivative and polarizability-derivative learning, an Equivariant Neural Kalman bridge for state-dependent refinement and reliability sensing, and an NBO-informed electronic-prior pa
arXiv:2609.28979v1 Announce Type: new Abstract: We study spectral graph neural networks built from Hermite polynomials and propose HermNet, a simple model that combines a nodewise predictor with normalized Hermite propagation. Its sparse recurrence requires neither eigendecomposition nor a learned basis. We distinguish the basic model from optional coordinate calibration, response normalization and Gaussian derivative regularization. Hermite and other complete polynomial bases span the same degree-bounded filter space, but their coordinates can produce different optimization behavior under limited training budgets. We analyze this behavior th
arXiv:2609.28998v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) has become a popular parameter-efficient fine-tuning method for large language models. A key challenge in LoRA is how to determine the rank of each adaptation matrix, as rank directly controls its capacity and efficiency. Existing adaptive-rank methods typically allocate ranks according to manually designed importance scores, which are not directly derived from an optimization objective. In this work, we propose $\ell_p$-LoRA, a principled rank-allocation method based on $\ell_p$ regularization with $0 <1$, which is a classical sparsity-inducing technique in signal pro
文章探讨了阿尔法一代（Gen Alpha）将“这太AI了”（That's so AI）作为一种负面评价甚至流行嘲讽用语的现象。该用语通常被年轻人用来指代虚假、公式化、缺乏个性或不动脑筋的低质创作。这一文化现象揭示了在生成式AI内容大规模渗透日常生活的背景下，年轻一代开始对流水线式的合成媒体产生审美疲劳与反感情绪，进而促使社会重新审视人类原创与真实表达的独特价值。
该素材涉及关于 Deepgram 举办的“Speak”语音 AI 大会（Voice AI Conference）是否值得参与的讨论链接。由于当前输入内容仅包含相关链接及极简的社区互动数据，并未提供关于该大会的具体议题、嘉宾阵容、举办形式或讨论详情等实质性信息，故有效内容不足，具体情况需参考原始网页进一步了解。
根据社交媒体与Hacker News讨论帖显示，Ruby on Rails创始人DHH（David Heinemeier Hansson）在Rails World活动上发言表示，由于AI现在能够制作应用程序，Ruby on Rails已不再被需要。目前素材仅提供该观点的讨论链接，缺乏现场演讲的具体上下文与详细阐述，信息较为有限，暂无法确认该说法属于严肃论断还是反讽修辞。
该文章题为“使用 AI 撰写论文的探索经历”，来自个人博客网站。由于输入素材仅包含文章及讨论链接，缺乏详细正文内容，具体信息相对有限。根据标题推测，文章主要探讨了作者在学术或技术论文写作过程中尝试运用人工智能工具的具体经验、使用心得或所遇挑战。因缺乏详细正文描述，具体的实践流程和核心结论暂无法详细展开。