独立 AI 资讯库
从自动抓取数据库实时读取，适合快速浏览、检索和后续扩展成完整资讯站。
arXiv:2608.11629v1 Announce Type: new Abstract: Audio transcription is a critical bottleneck in language documentation. While multilingual Automatic Speech Recognition (ASR) models like Whisper offer solutions, field linguists often lack the expertise to utilise them. We present Easper, an open-sou
arXiv:2608.11573v1 Announce Type: new Abstract: Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LLMs). In this work, we propose Self-Fix Step-DPO (SFS-DPO), a reinforcement learning based, two-stage
arXiv:2608.11552v1 Announce Type: new Abstract: Uncertainty quantification (UQ) methods for language models are typically evaluated on single-turn outputs, where uncertainty is attached to one generated answer. For LLM agents, however, the unit of observation is an interactive trajectory, where the
arXiv:2608.11534v1 Announce Type: new Abstract: In medical imaging, the clinical value of Computed Tomography (CT) lies not only in depicting current disease status, but crucially in enabling longitudinal comparison of serial scans to determine disease evolution, a process that underpins response a
arXiv:2608.11460v1 Announce Type: new Abstract: Large Language Model-powered agents are increasingly used in the workplace via human-artificial intelligence (AI) collaboration. In this new era of work, it is important to understand the kinds of prompting traits that contribute to task success. More
arXiv:2608.11350v1 Announce Type: new Abstract: Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces, and execution harness surrounding the model. While supervised fine-tuni
arXiv:2608.11338v1 Announce Type: new Abstract: Recently, the practice of augmenting LLM agent capability with skills has gained prevalence. We explore the cost effective adaptation of agents to novel domains by means of learning skills. Existing works focus on performance gain over cost effectiven
arXiv:2608.11236v1 Announce Type: new Abstract: Roleplay evaluation should do more than assign a single score: it should reveal which role requirements were tested, which failed, and which dialogue evidence supports the judgment. We propose TRACE Bench, a task-driven agentic checklist evaluation fr
arXiv:2608.11232v1 Announce Type: new Abstract: Evaluating LLM coding agents in algorithmic trading is difficult because static benchmarks risk data contamination and numerical backtest outputs require ground truth from actual code execution. We present Backtrader-Bench, a framework with two comple
arXiv:2608.11250v1 Announce Type: new Abstract: Language models can propose many plausible trading factors, but an autonomous research system must also allocate its evaluation budget, verify its own evidence, and preserve how each candidate was produced. We present AgonAlpha, an architecture that s
arXiv:2608.11248v1 Announce Type: new Abstract: Long-term memory is essential for language agents operating across extended interactions and evolving tasks. Existing memory-augmented agents mainly focus on storing and retrieving past experience, but the quality of stored memories may degrade over t
arXiv:2608.11247v1 Announce Type: new Abstract: Recent advances in language models have enabled collaborative settings in which multiple models leverage one another's capabilities, iteratively improving, transforming, and extending each other's outputs. Each agent sees what the others assert before
arXiv:2608.11246v1 Announce Type: new Abstract: The success of coding agents has established the harness as a paradigm: what an agent achieves depends not on the model alone, but on the infrastructure around it. We ask whether the same paradigm extends to embodied agents in the physical world. We p
arXiv:2608.11244v1 Announce Type: new Abstract: Construction standards are critical for building safety and sustainability. Existing standard application workflows rely on keyword-based document retrieval and manual cross-clause interpretation, which cannot reliably support multi-clause reasoning,
arXiv:2608.11243v1 Announce Type: new Abstract: We argue that a single structural fact organizes a wide range of phenomena in contemporary AI safety: a semantic safety constraint (e.g., the agent does not escape its sandbox) is an off-support object. Formally, if q is the data distribution and \(p(
arXiv:2608.11241v1 Announce Type: new Abstract: Deploying LLM agents into industrial recommender operations exposes a three-way tension we frame as the autonomy-determinism-efficiency trilemma: general autonomy (interpreting operator intent, generating glue code zero-shot), industrial determinism (
arXiv:2608.11238v1 Announce Type: new Abstract: Retrieval-augmented generation improves the factuality of large language models by grounding responses in retrieved evidence, yet existing evaluation frameworks struggle to provide consistent, fine-grained diagnostics across the diverse spectrum of us
arXiv:2608.11234v1 Announce Type: new Abstract: Managing modern computing infrastructure has become a steadily harder problem due to the ever-increasing complexity. Recent advances in AI agents create a timely opportunity to automate infrastructure management tasks, but it remains unclear how well
arXiv:2608.11229v1 Announce Type: new Abstract: Comparative feedback, asking people which of two behaviors they prefer, has become a standard way to align robot and agent behavior with human intent when the reward itself cannot be specified directly. Preference-based reward learning typically casts
arXiv:2608.11224v1 Announce Type: new Abstract: Materials research advances through accumulated experience - scripts that work, protocols that are trusted, warnings attached to failed calculations or experiments, and judgement that links a new question to an old result. This experience is essential
arXiv:2608.11218v1 Announce Type: new Abstract: Independent agents that reason in latent space can share computed state as key-value cache fragments rather than text. Merged by a conflict-free replicated data type, these fragments form a store that converges under any delivery order or duplication.
arXiv:2608.11216v1 Announce Type: new Abstract: World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe dominates across environments. This makes it an ideal testbed for AI coding agents acting as autonomous
arXiv:2608.11215v1 Announce Type: new Abstract: Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase behaviour, stylised facts, and scaling with the number of agents $N$, not the cognition of any sing
arXiv:2608.11211v1 Announce Type: new Abstract: Conway's 99-graph problem asks whether a strongly regular graph with parameters $\mathrm{srg}(99,14,1,2)$ exists. We report a systematic, fully reproducible attack by an autonomous AI research agent, scored under the track's partial-credit metric. Our
arXiv:2608.11210v1 Announce Type: new Abstract: Bayesian calibration of process-based models requires a prior distribution for each model parameter. Despite decades of methodological work, researchers almost always fall back on uniform priors. The main reason is that building informative priors fro
arXiv:2608.11207v1 Announce Type: new Abstract: When two LLM agents with structurally opposed objectives interact across multiple turns, the absence of a shared goal function produces not competition but collapse: the visitor capitulates, the site agent stops varying its approach, and the conversat
论文 MotionBlind 指出，视频大语言模型（Video-LLMs）虽然日益被用作世界模型的感知前端，但其运动理解能力存在显著缺陷。研究聚焦物体移动速度、运动方向以及受力强度等基础运动属性，并得出这些模型实际上无法可靠读取此类信息的结论。该发现意味着，开发者不应仅凭 Video-LLM 的语言描述能力推断其具备物理运动感知能力；在机器人、自动驾驶和世界模型等高风险应用中，仍需进行专门的运动理解评测与补强。论文编号为 arXiv:2609.09528v1，属于新发布论文。
Infra-Bench CLS 是一个用于关键基础设施分类的全球开源基准。该研究指出，关键基础设施的位置数据在全球范围内往往不完整且分布不均，发展中地区尤为明显。研究提出利用地球观测基础模型，更高效地理解和识别自然环境及基础设施相关信息。该基准可为开发者评估地球观测模型在关键基础设施识别任务中的能力提供统一参考。
在计算机断层扫描（CT）中勾画肺部肿瘤轮廓占据了放射治疗规划的相当一部分时间，而模型生成的预测轮廓可通过临床医生的交互操作进行微调。该论文提出了 LeCor 架构，探索通过元学习测试时训练（Test-Time Training）让模型具备高效“学习被修正”的能力。该方案结合了类似 SAM 等可提示基础模型在医学影像中的交互潜力，对加速临床放疗人机协同规划具有重要的技术参考价值。
视觉语言模型（VLM）在农业分类任务中展现出广阔前景，但在病虫害、农产品品质及物种识别等零样本任务中的表面性能仍不够理想。研究探讨了这种性能局限究竟源于底层视觉特征提取薄弱，还是输出与决策验证机制的失效。实验表明，通过引入基于量规（rubric-grounded）的结构化验证方法，能够有效弥合模型内蕴知识与实际输出间的差距。这一发现为垂直领域 AI 应用开发提供了新思路，表明通过设计精准的评价准则即可大幅释放通用多模态模型在专业场景中的潜力。