AI 测试必备：多Agent Skill 智能编排，从「脚本执行」到「失败自愈」到「报告生成」，一键跑通全流程！
前面几篇，我们分别分享了 api-test-executor（执行）、api-failure-diagnoser（诊断修复）、api-testdata-cleaner（数据清理）、api-report
独立 AI 资讯库
AI 前沿动态、原文归档与媒体镜像
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。
12101资讯
11969正文归档
76232媒体
:fire::fire: 2026 年，Java Agent 的最后一块拼图，终于被补齐了!
过去两年，Java AI 生态的发展非常快。 Spring AI、LangChain4j 等优秀框架，让 Java 开发者可以轻松接入 GPT、Claude、Gemini、DeepSeek 等各种大模型。 Chat、Prompt、Memory、RAG、Tool Calling、MCP、Agent…… 这些能力越来越成熟。 Java Agent，终于开始走进真实业务。 但当越来越多企业开始把 Agent 投入生产环境...
Agent 工程实习复盘 03｜从 Pickle 到 PostgreSQL：LangGraph Checkpoint 迁移、内存治理与可回滚发布
Agent 工程实习复盘 03｜从 Pickle 到 PostgreSQL：LangGraph Checkpoint 迁移、内存治理与可回滚发布 一、先说结论：这次改造解决了什么 我们原来使用本地 P
OpenAI and Hugging Face partner to address security incident during model evaluation
OpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.
Anthropic’s landmark $1.5B copyright settlement is approved
The final approval settles one case, but it doesn't resolve the broader issue of using copyrighted works to train AI models.
Eddy-VL 1.9B: Structural Pruning and Layered Distillation for Edge-Deployable Multimodal Embedding
arXiv:2607.16316v1 Announce Type: new Abstract: In this report, we introduce Eddy-VL 1.9B, a compressed multimodal embedding model built on Qwen3-VL-Embedding-2B for offline, edge-deployable vision-language retrieval. Eddy-VL targets air-gapped forensic and investigative settings where cloud APIs a
Seeing What Is Actually There: PriVE-Bench and PriVE-Tools for Counterfactual Evaluation of Agentic Visual Evidence in VLMs
arXiv:2607.16311v1 Announce Type: new Abstract: Vision-language models (VLMs) often answer visual questions using learned language and category priors rather than grounding their predictions in the image itself. Counterfactual images provide a natural diagnostic setting for this failure mode: when
SaaF: Scene-Specific Ambiguity-Aware 3D Language Fields towards Interactive Real-World Object Retrieval
arXiv:2607.16309v1 Announce Type: new Abstract: We propose Scene-specific Ambiguity-aware 3D Language Fields (SaaF), a novel Gaussian Splatting-based 3D language field designed for interactive object retrieval in a given real-world scene. Interactive object retrieval using natural language is a cru
CoBind: Stage-Aware Compositional Binding for Training-Free Text-to-Image Generation
arXiv:2607.16307v1 Announce Type: new Abstract: Diffusion-based text-to-image models often fail on complex prompts involving multiple entities, attributes, and relations, producing object omissions, incorrect attribute assignments, or reversed spatial layouts. Existing training-free methods mainly
LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models
arXiv:2607.16305v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding. However, scaling dense or sparse Mixture-of-Experts (MoE) models to improve performance limits deployment in resource-constrained environments due to the trade-of
Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillation
arXiv:2607.16303v1 Announce Type: new Abstract: Medical Vision-Language Models (Med-VLMs) require reliable reasoning from fine-grained visual evidence, yet existing models can produce plausible clinical answers by relying on language priors or medical templates rather than truly attending to diagno
Beyond Target Scores: Measuring Off-Target Drift in Diffusion-Based Medical Image Editing
arXiv:2607.16291v1 Announce Type: new Abstract: Diffusion models can now edit medical images in visually plausible ways, but the standard evaluation question is too narrow: did the target score increase? In clinical imaging, target findings are entangled with co-morbidities, acquisition effects, an
3D FaceShell: Attribute Transfer in 3D Face Avatars as a VLM Defense Mechanism
arXiv:2607.16280v1 Announce Type: new Abstract: Photorealistic 3D face avatars are increasingly deployed as reusable digital assets across applications such as telepresence, animation, and personalized media. At the same time, vision-language models (VLMs) can infer sensitive attributes from render
A Step Forward Towards Trustworthy Risk-Aware Facial Retrieval (RA-FR)
arXiv:2607.16279v1 Announce Type: new Abstract: Facial image retrieval in unconstrained surveillance environments is a high-stakes challenge where missing a subject of interest -- a single false negative -- is simply not an option. Despite near-perfect performance on curated benchmarks, current rec
Feature Generation Using LLMs: An Evolutionary Algorithm Approach
arXiv:2607.16255v1 Announce Type: new Abstract: A crucial step in machine learning pipelines is to present each entity with features or attributes that are representative of the characteristics of the processed entities. Feature engineering is an important step in finding a relation among attribute
More Than Memory: Task-Conditioned Signed FFN Writes in Long-Context Retrieval
arXiv:2607.16254v1 Announce Type: new Abstract: FFNs are often treated as parametric memories. In long-context retrieval, however, the sharper question is not only what they store, but whether their native residual writes push the current retrieval state toward or away from the correct answer. We t
Self-Evolving Just-In-Time Memory for Proactive Embodied Safety
arXiv:2607.16247v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions. Existing safety approaches often rely on runtime g
CIGPO: Contextual Information-Gain Policy Optimization for Multi-Turn Evidence-Reading LLM Agents
arXiv:2607.16244v1 Announce Type: new Abstract: Training multi-turn evidence-reading agents with outcome-only reinforcement learning is unstable because intermediate turns receive little direct credit. In HotpotQA experiments with Qwen2.5-3B-Instruct, GRPO initially improves (standard F1 0.430) but
RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants
arXiv:2607.16243v1 Announce Type: new Abstract: Multimodal industrial anomaly inspection assistants are a critical component of next-generation smart factories, enabling interactive vision-language-based querying. However, multimodal large language models remain impractical for on-site deployment d
Quantizing Recursive Reasoning Models
arXiv:2607.16237v1 Announce Type: new Abstract: Recursive reasoning models solve hard puzzles by applying compact, weight-tied blocks over many refinement steps. Because these blocks are reused many times, quantizing them creates a unique dynamical problem: the quantization error is incurred at eve
RouteCost: A Production-Inspired Multi-Stage Framework for Pre-Order Shipping Cost Estimation in E-Commerce
arXiv:2607.16230v1 Announce Type: new Abstract: Accurate pre-order shipping cost estimation is important in e-commerce because it affects price presentation, margin planning, and conversion. In practice, shipping cost is shaped not only by distance but also by destination demand mix, billable weigh
DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth
arXiv:2607.16203v1 Announce Type: new Abstract: Document parsing is a foundational step for document understanding tasks such as visual question answering and key information extraction, as it transforms unstructured scanned images into structured representations by extracting textual, visual, and
Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph
arXiv:2607.17266v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these iss
Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?
arXiv:2607.17262v1 Announce Type: new Abstract: Existing methods for multimodal sentiment analysis (MSA) under missing modalities usually follow a repair-first paradigm. We revisit this assumption and ask: \emph{should every missing modality be repaired?} A per-sample oracle analysis shows the answ
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World
arXiv:2607.17250v1 Announce Type: new Abstract: This paper introduces EvolvingWorld, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive literary simulation as static persona imitation or isolated scene generation,
AI_LectureNote: A Retrospective Pilot Study of a Post-ASR Workflow for English-Script Rendering and Semantic Drift in Korean-English Medical Lectures
arXiv:2607.17237v1 Announce Type: new Abstract: AI_LectureNote is a historical, readability-oriented post-ASR workflow for Korean-English medical lectures. It rewrites speech-to-text output into study transcripts while restoring Latin-script medical terms rather than Korean phonetic transliteration
Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries
arXiv:2607.16989v1 Announce Type: new Abstract: Introduction. Clinical and Translational Science Award (CTSA) programs must document their scholars' research impact, but assembling each scholar's record by hand takes staff an estimated 15 hours and does not scale to a full cohort. An artificial int
Trace-Based On-Policy Distillation for Masked Diffusion Language Models
arXiv:2607.16872v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. However, reasoning-oriented post-training for dLLMs remains challenging. Supervised fine-tuning (SFT) for dLLMs requires dense but often off-policy maske
JOR-Bench: Japanese Operations Research Benchmarks for Large Language Models
arXiv:2607.16777v1 Announce Type: new Abstract: We present JOR-Bench, a collection of five Japanese-language benchmarks for evaluating the ability of large language models (LLMs) to formulate and solve operations research (OR) problems. Each benchmark is a Japanese translation of an existing Englis
Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation
arXiv:2607.16704v1 Announce Type: new Abstract: Large language models frequently violate fundamental scientific principles when generating technical content, undermining their reliability in scientific applications. We introduce Scientific Feasibility Control SFC, a graph-structured conformal predi