aigencc
SIGNAL, NOT NOISE
全部简报
YOUR DAILY INTELLIGENCE

2026 / 10 / 20.

这一天，值得记住的 AI 动态。

12 SIGNALS · ARCHIVED EDITION生成于 2026/10/20 21:12:15（北京时间）
研究论文

Manga2Animate：多智能体漫画动画框架

论文提出 Manga2Animate，一个多智能体框架，用于将现有漫画改编为忠实原作的动画。作者将任务分解为动画脚本与视觉分镜两种中间表示，每种表示由创建智能体生成，并由配对的审阅智能体对照原漫画分格进行审查，再通过针对表示的选择机制和双层反馈逐步精炼，最后合成动画。论文称实验与用户研究显示，该方法比现有方法更忠实于原作、镜头间一致性更好。

HDaily Papers·
研究论文

MemT-1.0：迈向记忆原生演化

论文提出记忆基础模型架构 MemT-1.0，将记忆内化为模型计算的一部分。它基于 Metis，采用 Gated DeltaNet-2 与稳定的 token 级记忆更新机制，并引入 Mixture-of-Storage 扩展原生记忆容量。作者报告，该模型在记忆与通用能力评测中平均优于参数化记忆基线，与检索增强方法相当，并基本保持通用能力。

XarXiv · cs.CL·
研究论文

参数高效微调扩展至脑编码模型

论文提出用参数高效微调（PEFT）适配大型预训练骨干网络进行脑编码，利用骨干的因果结构单次预测多个时间点以降低特征提取成本，可微调多达104B参数的多模态模型。作者报告在九个多模态骨干上性能一致提升，BrainLoRA在Algonauts 2025挑战赛取得已发表最佳成绩，并开发多LoRA内核支持200+模型集成。

HDaily Papers·
研究论文

Holi-World：从人类自我中心经验构建世界智能

论文提出 HOLI-WORLD 生态，整合经验采集、世界表示、自动数据构建、模型学习与独立评测。其 Foundry 模块结合静态与动态感知自动生成世界记录，Data 将约 100 个自采场景整理为约 8 万 QA 对，用于训练 HOLIWORLD-VL-4B；HOLIWORLD-Bench 由人工标注留出录像构成。作者报告在 ScanNet、ScanNet++、Aria Digital Twin 及该基准上静态感知与动态跟踪表现良好，训练后模型在时空推理上明显提升。

HDaily Papers·
研究论文

ScaleNav：利用互联网视频预训练语言条件局部导航

论文提出 ScaleNav，一个面向语言条件局部导航的世界-动作统一框架，分三阶段训练：先用互联网第一视角视频做指令条件视频预训练，学习相机接近指定目标时的视觉动态；再用带动作标注的仿真数据做动作对齐，训练模型预测可执行动作块；最后联合微调全部可训练组件。作者报告在 Short-Horizon OVON 单视角适配版本上成功率达 86.5%，在 HabitatGS-LN 基准上达 94.9%，并在真实四足机器人上部署评估。

HDaily Papers·
研究论文

Selm: Self-Evolving Library Management for Multi-Skill Agent Optimization

arXiv:2610.24630v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly use skills as a lightweight way to acquire task-specific knowledge. Recent work enables skills to evolve from task trajectories. However, these methods often lack systematic management of evolved skills, making it difficult for agents to reuse and accumulate skills across domains, thus limiting performance on subsequent tasks.To reliably accumulate, reuse, and maintain useful skills across tasks, we present SELM (Self-Evolving Library Management), a framework that formulates skill evolution as library-level management. SELM jointly manages skill retrieval, updating, and lifecycle by maintaining skill confidence and utility signals. It introduces utility-aware retrieval to select useful skills, a Map-Reduce framework to generate targeted updates from task-specific experience, and lifecycle controls to retain or remove skills based on their effectiveness. These mechanisms enable the skill library to continuously accumulate useful experience while preserving and pruning skills across tasks, improving agent performance on complex tasks across diverse domains. We evaluate SELM on four agent benchmarks covering diverse tasks and execution environments, and SELM consistently outperforms in most settings.

XarXiv · cs.AI·
研究论文

Teaching Code Agents to Ask Without Leaking Private Code

arXiv:2610.24824v1 Announce Type: new Abstract: Local coding agents can extend their reach by consulting a stronger cloud model. Such consultations, however, often expose the repository's private identifiers, file paths, and source code. Host-side masking hides recognized identifiers but leaves the surrounding code and the agent's phrasing unchanged, while training for less disclosure risks suppressing consultation or producing questions too vague to answer. We propose utility-verified abstraction (UVA), which teaches the agent to describe private entities by their role and type while retaining the technical details an expert needs. From solved repair trajectories, we rewrite each question into this form and keep the rewrite only if it discloses fewer private entities and the repair, replayed from the same execution state with the repair trajectories. Across two benchmarks, the trained agent consults more often than before training. On repository-level issue repair, it solves 37.6% of issues, against 25.3% for the same model working alone, a gain from the training as a whole rather than from consultation alone. Its questions disclose 3.7-fold fewer private entities and 1.4-fold less verbatim code than the untrained agent's questions to the same expert.

XarXiv · cs.AI·
研究论文

Pattern-Driven Evaluation of LLM Code Optimization: Isolating Compiler-Transcendent Semantic Reasoning

arXiv:2610.24835v1 Announce Type: new Abstract: Existing evaluations of LLM-based code optimization primarily measure end-to-end speedup, obscuring whether a model actually performs the intended optimization. For compiled languages, this is especially problematic: observed gains may reflect transformations already recoverable by modern optimizing compilers rather than optimization behavior attributable to the model itself. We present PatternBench, a benchmark for studying compiler-transcendent optimization, i.e., performance improvements that remain after aggressive compiler optimization. PatternBench targets residual optimization opportunities across seven classes of transformations and pairs runtime evaluation with an AST-based optimization faithfulness analysis that verifies whether the intended optimization is realized in the generated program. Experiments with frontier, open-weight, and fine-tuned models show that runtime speedup alone provides an incomplete account of optimization capability. Optimization faithfulness is strongly associated with realized speedup, and fine-tuning improves both faithfulness and optimization effectiveness. These results suggest that evaluation of LLM-based code optimization should measure not only performance outcomes, but also whether the target transformation was successfully executed.

XarXiv · cs.AI·
研究论文

OpenSaC: A Python Library for Search as Code in Deep Research Agents

arXiv:2610.25779v1 Announce Type: new Abstract: Deep research agents investigate complex questions through iterative search, source examination, and evidence synthesis. A conventional workflow alternates reasoning with individual search and reading actions. Search as Code introduces a new paradigm: agents write programs that compose search, source reading, reranking, model calls, and local processing, returning selected observations for further reasoning. To support this workflow in existing coding agents, we present OpenSaC, an open-source Python library with a companion Search as Code skill. Configurable capability interfaces let agents combine these operations while retaining evidence for inspection and reuse. Compared with standard Codex using its built-in web search, the OpenSaC configuration uses less execution time and fewer model tokens on BrowseComp and WideSearch, with higher accuracy on BrowseComp and slightly lower row F1 on WideSearch. We aim to lower the barrier to adopting Search as Code and provide an open foundation for community development and transparent research on deep research agents.

XarXiv · cs.AI·
研究论文

From Code to Playable Systems: CEGame-Bench for Long-Horizon Game Creation Agents

arXiv:2610.26098v1 Announce Type: new Abstract: A game ships when a player can launch it, finish it, and return to a saved world, none of which a successful build guarantees, yet game-creation agents are mostly tested on one engine or on one-prompt browser games. We present CEGame-Bench, the first long-horizon benchmark for complete-game creation across five production engines: Defold, Godot, Roblox Studio, Unity, and Unreal Engine. Agents build each game from an empty project and a design document in runs averaging up to 295 steps and 65M tokens; the document doubles as a contract, and a hidden evaluator accepts a game only by real-input play. Under four scaffolds, agents earn most integration points but usually under half the gameplay points, and their games reach the ending in only 16% of runs, while references built by engineers with coding agents score near the maximum, which places this artifact-to-play gap in the agents. No two engines rank configurations alike (Kendall's tau 0.14-0.62), and the same game usually scores higher on Unity and Unreal Engine, which check more before play. We release Game Completion Boost, an agent skill for requirement-driven playtesting and repair that raises the execution-based score of three models by 14.1-24.3 points.

XarXiv · cs.AI·
交叉发布

Does AI-Assisted Development Homogenize Software? An Empirical Study of Code Similarity, Quality, and Evolution

arXiv:2610.24093v1 Announce Type: cross Abstract: AI-assisted software development is evolving from interactive LLM assistance toward agentic systems that autonomously perform software engineering tasks, yet the effects of this shift remain insufficiently understood. We present an empirical study of 50 long-lived Java and Python open-source projects across three eras: pre-LLM, potentially LLM-assisted, and detected agentic development. Using snapshots from Software Heritage, we examine code similarity, software quality, and software evolution. Similarity is measured semantically through embedding-based cosine similarity and syntactically through CodeBLEU*. Quality is assessed with SonarQube metrics covering maintainability, complexity, reliability, and security. Evolution is characterized by annualized growth rates of LOC, functions, classes, files, and statements, and by commit activity in the three months preceding each snapshot. Results show no consistent evidence of increased similarity as semantic and syntactic similarity decreased significantly in Java for both the LLM and agentic eras relative to the pre-LLM era, while Python showed no significant differences. Software quality remained largely stable, although the agentic era showed significantly lower code-smell and SQALE index densities. Structural growth was generally lower in the agentic era, particularly for files, whereas development activity increased moderately in Java, especially in commits and added lines. These findings challenge the assumption that LLM- and agent-assisted development necessarily homogenizes code, degrades quality, or accelerates growth.

XarXiv · cs.AI·
交叉发布

Model Capacity Frontier: A Development Framework for LLM-Supported Social Simulation

arXiv:2610.24168v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly incorporated into agent-based models (ABMs) on the premise that richer, context-sensitive human behavior can improve empirical fidelity. However, LLM-supported ABMs introduce an open-ended design space in which subtle modeling and configuration choices, such as prompt design and environment coupling, can substantially alter outcomes. Developing LLM-supported ABMs to simulate human collective behavior therefore requires navigating configuration sensitivity while identifying the limitations of the current model architecture. In this paper, we introduce the \textit{Model Capacity Frontier} (MCF), a framework that characterizes the empirical performance attainable by a specified architecture across its admissible configurations. In multi-objective settings, this capacity is represented by an estimated Pareto frontier obtained through systematic configuration exploration. We demonstrate MCF in crowd simulation of university commencement events with approximately 12,000 agents, using empirical movement data on temporal occupancy, spatial distribution, and flow direction. We first characterize the capacity of a conventional crowd model and then evaluate successive LLM-supported architectural extensions. In the process, MCF reveals which dimensions of attainable performance expand and which remain limited, providing empirical targets for refinement and re-evaluation. Initial LLM integration improves flow direction but degrades temporal occupancy and spatial distribution; subsequent architectural refinement of the LLM layer improves temporal occupancy and recovers spatial performance, while retaining much of the earlier gain in flow direction. Our case study shows how MCF guides the systematic architectural development of LLM-supported ABMs in configuration-sensitive, open-ended design spaces.

XarXiv · cs.AI·