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:2607.12334v1 Announce Type: new Abstract: Retrieval-augmented question answering depends on selecting evidence passages that jointly support answer generation. However, many RAG pipelines rely on top-\(k\) ranking, where passages are selected mainly by individual relevance scores, even though
arXiv:2607.12310v1 Announce Type: new Abstract: While modern question answering (QA) systems excel on clean, schema-aligned corpora, real-world knowledge is rarely so neatly packaged. Answering questions over enterprise and scientific data lakes requires systems to navigate heterogeneous, weakly st
本文提出了无需人类专家参与即可大规模生成评估标准的可扩展流程，基于104个真实用户查询构建金融深度研究基准，并自动合成14,450条候选评估项。通过比较人类专家与三LLM评判小组，显示LLM评估与人类具有98.67%的标签一致性，足以替代人类执行大规模筛选。经过严格一致性与可区分性过滤，最终得到2,600条共识金标准，据此对10个深度研究系统进行排名，通过率从58.58%到22.23%不等，清晰区分了系统质量，该流程对开发者自动化评测与系统迭代具有重要借鉴意义。
arXiv:2607.12233v1 Announce Type: new Abstract: Large language model (LLM) trading agents show promising performance in equity markets, yet remain narrowly focused on US equities with little evidence from live deployment. We present Fin-Analyst, a hybrid agent for FinMMEval 2026 Task 3: an eight-sp
arXiv:2607.12216v1 Announce Type: new Abstract: Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instructions, inside the same finite prompt used for the current task. This creates a practical allocation
arXiv:2607.12215v1 Announce Type: new Abstract: Accurately assessing personality from text is challenging because traits are latent, context-dependent, and often subtly expressed across long narratives. Large language models (LLMs) offer new opportunities by processing extensive textual contexts, b
语义记忆检索可被理解为在概念空间中的导航。本研究借助语言流畅性数据，对比了人类与 GPT-4o、Gemini-2.5-Pro、Claude-Sonnet-4.5 三种大语言模型的语义搜索动态。分析揭示了模型与人类在概念空间遍历模式上的异同，为理解大模型的知识组织方式提供了认知层面的参照。该工作对开发更类人的 AI 智能体以及认知诊断工具具有参考意义。
一篇新论文指出，针对 API 编码 Agent 的上下文缩减层（如命令输出压缩、检索排序、有效载荷代理）通常只衡量删除的文本量，而忽略了这些缩减何时才真正带来成本下降。该研究提醒开发者，在优化 Agent 管线时不应将 Token 数量减少简单等同于实际成本降低，需要建立更全面的评估标准。
arXiv:2607.12086v1 Announce Type: new Abstract: Recent LLM-based multi-agent urban simulators can generate semantically rich city routines, but they remain costly to scale and are often weakly validated against empirical mobility patterns. We present CityBehavEx, an interactive LLM-assisted urban s
arXiv:2607.12051v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being explored for clinical decision support, but their reliability in complex oncology treatment planning remains unclear. We evaluated agentic LLM systems for breast cancer treatment recommendation gener
arXiv:2607.11933v1 Announce Type: new Abstract: Cross-encoders achieve high reranking accuracy in Retrieval-Augmented Generation (RAG) pipelines but impose quadratic inference costs that limit real-time deployment. We address this by fine-tuning LLaMA 3 (8B) as a drop-in reranker using a two-stage
arXiv:2607.11892v1 Announce Type: new Abstract: Human-factor event diagnosis is essential for learning from operational events in nuclear power plants, yet its quality depends strongly on expert interpretation of narrative reports and guideline-based reasoning.Existing data-driven or one-shot large
arXiv:2607.12520v1 Announce Type: new Abstract: What a frontier model recalls about a person or tool from its own weights -- before any retrieval step -- often shapes the first description a human sees, making that parametric corpus presence a measurement problem. Citations explain about a third of
arXiv:2607.12480v1 Announce Type: new Abstract: This paper defines TRACE (Typed Reasoning And Commitment Evidence): a typed, versioned schema for recording reasoning traces, a reference procedure for writing records against it, and one operating discipline, no durable state change without a record.
这篇论文提出函数感知的中间填充（Fill-in-the-Middle）方法，作为编码代理基础模型的中期训练策略。研究者指出，标准从左到右的代码预训练无法充分建模代理调用外部工具后整合返回结果的推理过程，而代理的动作-观察-延续循环与中间填充任务高度一致。通过函数感知的中期训练，模型能更好地学习代码上下文修复与工具调用衔接，有望提升编码代理在复杂软件开发中的性能。
arXiv:2607.12406v1 Announce Type: new Abstract: The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only about input--output content alignment. It also concerns system behavior
arXiv:2607.12397v1 Announce Type: new Abstract: LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger irreversible side effects long before the final failure is observed. R
PM-Bench 是一个基于文本的基准，用于衡量大语言模型 Agent 的前瞻记忆能力，即在进行其他活动时在特定未来线索或状态下执行意图的能力。研究发现，即使是最强的模型，如 o4-mini-high 和 Gemini 3.0 Pro，在复杂前瞻记忆任务中也仅在 80% 左右的得分，模型在前瞻编码、意图维持与触发识别方面存在明显弱点。该基准为开发者提供了前瞻记忆的标准化评估框架，揭示了当前 Agent 架构在长期、多任务场景中的关键局限，对推进自主 Agent 的实用化具有重要意义。
该论文探讨智能体基准测试中，仅执行部分任务能否得出与完整运行一致的成对比较结论。作者指出，由于完整评估成本高昂，部分任务运行虽具吸引力，但仅凭任务完成比例无法判断其结论是否可靠。研究通过复盘公开的大语言模型智能体基准，为开发者提供关于基准测试效率与准确性的新认识。
端侧研究智能体在个人笔记本上检索语料、阅读来源并生成带引用的简报。该研究首次在 24 GB 显存的设备上固定一个 4B 生成模型，量化了可部署小模型引用的忠实度与成本。结果表明，模型的数据曝光程度制约其引用忠实度，而检索范围则直接影响内容的覆盖率。对开发者而言，这意味着在资源受限的端侧场景中，需通过优化上下文窗口与检索策略来平衡可靠性与完整性。
本文重新审视了面向LLM智能体的自动框架演进评估。现有方法基于单元测试用例搜索框架配置，并在同一公开基准上报告最终性能，这一评估协议引发了对公平性与泛化性的关注。该工作对开发者构建更可靠的智能体评估体系具有参考意义。
企业在多租户大型语言模型（LLM）系统中部署检索增强生成（RAG）时面临关键的治理缺口：生成成本可按 token 精细计量，但检索层（向量存储、相似度计算与嵌入 API 调用）的成本却缺乏归属，成为无人认领的共享开销。该论文提出“成本治理的 RAG”方法，旨在将检索与生成环节统一纳入每租户成本归属框架。这项研究对开发者构建可运营、可计费的企业级 RAG 应用具有重要指导意义，有助于实现多租户场景下的资源透明管控与公平计价。
arXiv:2607.12177v1 Announce Type: new Abstract: The analysis of satellite and aerial imagery has entered a new era with the advent of foundation models. This paper describes the concept of Geospatial Foundation Models (GeoFMs), which are artificial intelligence/machine learning (AI/ML) models pre-t
arXiv:2607.12085v1 Announce Type: new Abstract: Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality. Although LLM-as-a-judge methods provide scalable alternatives to
arXiv:2607.12077v1 Announce Type: new Abstract: Multi-agent language-model systems increasingly route local interactions, yet the runtime interaction graph is often treated as an implementation detail. We study convention formation in open-weight LM populations spanning 1.1B-32B parameters with a n
arXiv:2607.12056v1 Announce Type: new Abstract: Online shopping is increasingly shifting toward a model in which AI agents independently search for products, compare options, evaluate constraints, and carry out parts of the purchasing process for users. Website design must now support both human an
arXiv:2607.11977v1 Announce Type: new Abstract: In 2019, OpenAI released two million GPT-2 outputs-ungrammatical, half broken-to aid the detection of machine-generated text. The alignment that produced their more fluent successors is usually regarded as an engineering achievement; we read it instea
arXiv:2607.11906v1 Announce Type: new Abstract: The development of decision-pretrained transformers, algorithm distillation, long-context meta-RL, and retrieval-augmented agents has renewed interest in in-context reinforcement learning (ICRL): the ability of a pretrained or fine-tuned decision mode
评估显示，面向领域的 Earth AI 技能对于提升 Agent 的空间推理能力至关重要。仅配备网页搜索、地图定位和代码执行等基础工具的 Agent，在定量空间任务上表现较弱；加入 Earth AI 技能后，其在 GeoExpertQueries、GeoKTools 和 CBGB 基准上的成绩显著提升。对于开放式真实世界工作流，前期规划能够帮助 Agent 完成多步骤分析，减少不可靠假设以及以网页搜索替代空间工具等捷径行为。UnivEARTH 是例外，即使独立 LLM 也取得了 93.6% 的分数，可能因为相关 NASA 文章及答案可在公开网络上获取。
流式视频生成在世界建模中具有重要潜力，需要在线、按顺序地预测未来帧，从而形成连续的视频流。原文指出，流式视频扩散模型存在根本性的训练—推理不匹配问题。该研究提出“流强制”（Stream Forcing），旨在构建统一的训练轨迹，以提升流式视频生成的鲁棒性。由于所提供原文未包含完整摘要和方法细节，具体技术实现、实验数据及结论尚无法进一步确认。