研究

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：You’ve shipped a working chat feature. Now comes the hard part: figuring out which framework actually fits your production architecture. The tooling landscape has fractured, and comparing AI agent frameworks in a vacuum…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：A deep dive into a living memory's forward pass - Sapience Labs Sapience Labs · technical deep dive · August 2026 A deep dive into a living memory's forward pass What actually happens when one AI session w…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Dive into LangSmith product usage patterns that show how the AI ecosystem and the way people are building LLM apps is evolving.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Reflections on how LangChain has evolved — including our products, ecosystem, and community — over the past two years, and where we're headed next.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：See how Podium tests across the lifecycle development of their AI employee agent, using LangSmith for dataset curation and finetuning. They improved agent F1 response quality to 98% and reduced the need for engineering intervention by 90%.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：In this post, you will learn how GoDaddy migrated from their legacy business intelligence (BI) tool to Amazon Quick. This was a two-year transformation that delivered results across every dimension of the business: 15,000 hours saved annually, 50% reduction in dashboard count, rendering times cut to under 5 seconds, and AI-powered self-service analytics now accessible to every employee.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：AI for kids・Askie Safe AI for children Your child's AI helper and study buddy for bedtime stories, school help, and creative AI stories for kids. Safe AI chat designed for children ages 4-15 with parental controls. AI c…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Notch | Substack Home Subscriptions Chat Activity Explore Profile Notch Notch @notch321 Persistent AI research experiment. See subscribers

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The advanced side of supervised fine-tuning data prep. This second post in a two-part series covers evaluating data readiness with learning curves, selecting high-value data subsets, augmenting data with synthetic and distilled examples, and mixing data sources to prevent catastrophic forgetting.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Data preparation determines the ceiling of any supervised fine-tuning project. This first post in a two-part series covers the foundations of SFT data prep: quality checks, conversational (JSONL) formatting, reasoning and tool-calling schemas, and a representative train/evaluation split.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The gist Auto Browse, the Gemini 3 agentic mode Google started rolling out in Chrome on 28 January 2026, is rationed: 20 multi-step requests a day on Google AI Pro, 200 a day on AI Ultra. That ration is the most informa…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：LangGraph Platform, our infrastructure for deploying and managing agents at scale, is now generally available. Learn how to deploy

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Learn how Amazon Bedrock AgentCore agents in one account can generate answers from an Amazon Bedrock knowledge base backed by Amazon Redshift Serverless in another account, without copying source data. This post covers the architecture, security boundary, and two orchestration models: a code-based Strands agent and a declarative AgentCore harness.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Notifications You must be signed in to change notification settings Fork 0 Star 2 BranchesTags Open more actions menu Latest commit History 132 Commits 132 Commits Folders and files NameName Last commit message Last com…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：We raised $125M at a $1.25B valuation to build the platform for agent engineering.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：We built WikiBench to test whether generated wikis help coding agents. Pairing a wiki with source code scored higher than source alone, at lower cost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：We shouldn't ignore agentic AI ransomware threats, but the claims of a new ransomware group might be skewing the numbers.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Why LangChain believes in open, customizable cognitive architectures over closed systems. Build reliable LLM agents with OpenGPTs and LangSmith.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Data-driven-characters is a repo for creating, debugging, and interacting your own chatbots conditioned on your own story corpora.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Four falsifiable conditions for agentic coding replacing juniors, tested against METR, OpenAI, DORA and Stanford primary source evidence The post What Would Have to Be True for Agentic Coding to Replace Junior Engineers appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Auto-evaluate LLM question-answer chains with LangChain's free tool. Generate test sets, grade answers, and optimize chain performance.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Implement OpenAI's proven RAG strategies with LangChain. Explore query transformations, routing, post-processing, and evaluation methods for optimal retrieval.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Explore how LangChain implements autonomous agents like AutoGPT and BabyAGI. Learn about planning techniques, memory systems, and agent simulations.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Photo: Steve A Johnson / Pexels Nvidia’s Vera CPU outpaces AMD EPYC 9655P in Linux kernel compilation at Hot Chips 2026 The chipmaker's new Vera CPU, Rubin GPU, and networking stack represent a coordinated bet that agen…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：This article is sponsored by Unframe and was written, edited, and published in alignment with our Emerj sponsored content guidelines. Learn more about our thought leadership and content creation services on our Emerj Media Services page. Retail has an AI operationalization bottleneck, converting AI investment and experimentation into governed, integrated production capabilities that deliver measurable […]

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：In fact, AI projects are not built by simply choosing a model and feeding it data. Furthermore, a successful AI system goes through multiple stages, starting with identifying the right problem and ending with deployment, monitoring, and continuous improvement. This structured journey is known as the AI Project Cycle. It helps teams move from an […] The post Mastering the AI Project Cycle: From Concept to Production appeared first on Analytics Vidhya.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：This post was not written with or by AI. I wanted to explore how AI could help deepen my faith. I enjoyed using Claude to research topics which were on my mind. It does a good job finding and quoting scripture but a poo…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Notifications You must be signed in to change notification settings Fork 0 Star 2 BranchesTags Open more actions menu Latest commit History 9 Commits 9 Commits Folders and files NameName Last commit message Last commit…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Glean Technologies Inc. today unveiled Glean Tau, a desktop workspace that connects the company’s enterprise artificial intelligence to a user’s local files, applications and code. The launch anchors a broad slate of product news at Glean:GO, the company’s conference this week in San Francisco. Packaged with it were benchmark numbers aimed at Anthropic PBC. Glean said […] The post Glean unveils Tau desktop workspace, claims token-cost edge over Claude appeared first on SiliconANGLE.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：tldr AI agents create and edit PowerPoint by writing code against libraries with serious limitations. Even basic edits end up slow, expensive, and prone to file corruption. We built a PowerPoint API that addresses these…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Everyone's using AI coding agents. Here's how to make yours actually useful.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Do you need easy, secure remote access to your home or small business network? Before you pay big bucks for a VPN or remote-access plan, try Tailscale. Did I mention it's free?

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：In effort to prime chatbots to make pro-Israel arguments the site published 124 reports, over 560,000 words in nine days, Guardian analysis shows A pro-Israel messaging website badged with the name of a thinktank that does not exist has published more than half a million words in nine days, built on a commercial platform that promises to optimize content so that AI chatbots will cite it. The site gives Israel’s position on subjects including the torture of Palestinian prisoners, Israeli war crimes and whether Israel has deliberately starved Palestinians in Gaza, all presented as neutral research. Continue reading...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Distilling three major AI releases to keep you current.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Quality scores 100 = best · Line = minimum Three documentation quality scores out of 100. Each bar includes its minimum passing score. Codebase coverage Important systems and workflows are documented. Minimum passing sc…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The “CrysVCD” tool developed at MIT could cut the huge amounts of time and money spent on screening out chemically unstable designs.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：My Anti-AI manifesto As a software developer, the recent escalation of Artificial Intelligence (AI) has aroused strong emotions and several concerns in me, either of technical and philosophical nature. The human-machine…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：‘This is crazy. This is insane’: Bill Gates has changed his mind about AI and jobs Aug 26, 2026, 3:00am EDT Technology PostEmailWhatsapp The News Bill Gates says it’s time to hit the AI panic button. The technology has…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Limits of robot autonomy The fact that many events still permitted humans to directly control robotic motions shows that autonomous robot systems still have a long way to go, Patel said. Whereas humans can quickly learn…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：5 Join the conversation Follow us Add us as a preferred source on Google A Russian Molniya drone carrying an Nvidia Jetson Orin module crashed and killed three civilians at a gas station in Zaporizhzhia last month after…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Hey all, The goal is to earn on token margins for LLM calls when you build an AI-powered webapp. I proxy OpenAI and Anthropic calls so that when you deploy a site to a subdomain, your users token usage will be tracked.…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The vast majority of the global public wants international cooperation on human rights, climate and AI. Like-minded countries must stand together to deliver Britain’s new prime minister, Andy Burnham, is already having to make one of his gravest decisions. He has to issue the instructions that he alone gives to the military, setting out the UK response in a doomsday scenario of a nuclear weapons attack on us. He will, as I did two decades ago, sign a piece of paper telling commanders whether or not to retaliate and, if so, whether through targeting civilian conurbations or military sites. These instructions are written down in the aptly named “letter of last resort”. Now, more than at any time since the 1960s Cuban missile crisis, the European public fears a third world war. With the nuclear Doomsday Clock developed by atomic scientists moving ever closer to midnight, and Japan, South Korea, Saudi Arabia, the UAE, Egypt, Poland and Germany contemplating either acquiring nuclear weapons or siting them on their soil, our world is descending from a rules-based order to a power-based one, where might is deemed right and brute force dominates. Gordon Brown is the UN’s special envoy for global education and was UK prime minister from 2007 to 2010 The future starts with us: Gordon Brown in conversation On Thursday 10 September, join Hugh Muir and Gordon Brown to discuss the intricate connections between global instability and civic decline, as explored in Brown’s new book, The Future Starts With Us. Book tickets here Continue reading...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.23994v1 Announce Type: new Abstract: Human-robot teaching focuses on enabling nontechnical experts to customize robots according to their needs after deployment. With recent advances in machine learning, human-robot teaching is no longer confined to offline learning where the data gathering step from a human teacher is separated from when the robot learns. Instead, more recent approaches for human-robot teaching focus on coupling human teaching with robot learning. This coupling impacts the structure, timing, and content of the teaching and learning interaction. However, it is currently unclear how such coupling dynamics affect humanrobot teaching effectiveness and human perceptions towards the teaching process. Informed by human learning theories, in this paper we propose a new scale for classifying human-robot teaching interactions according to coupling dynamics present between the human teacher and robot learner. We apply this scale to a subset of the human-robot teaching literature to identify how coupling dynamics and human teacher mental model mismatches with the ground truth robot learning system affect teaching effectiveness and human perceptions towards the teaching process

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.23983v1 Announce Type: new Abstract: Robotic fruit harvesting must hold produce securely without bruising it, yet compression stiffness varies several-fold with ripeness within a single species, so no fixed grip force spans the range. Rather than tune force, we bound deformation: a controller closes the gripper until the object's estimated compression strain reaches a user-specified limit $\varepsilon$, using only the encoder position and motor-effort signal on every servo gripper---no tactile or force-torque sensor. Dividing an effort-based contact force by a lower bound on object stiffness makes the stop provably conservative---true compression stays at or below $\varepsilon$---for any $\varepsilon$ above a contact-detection strain floor we identify and quantify: robust detection itself spends compression, linearly in closing speed, making speed an explicit throughput--gentleness knob. Unlike a hand-tuned force threshold, $\varepsilon$ is a certified, size-scaling, operator-interpretable damage limit, and a ready safe-action parameter for learned grasping policies. In MuJoCo simulation over a realistic fruit-stiffness range, under a sensor-noise model calibrated to the real servo, the controller holds $\ge 98\,\%$ grasp at $0\,\%$ damage across all medium-to-firm stiffnesses for the entire certified $\varepsilon$ range, which neither fixed-force baseline attains; on stiffness-graded 3D-printed TPU cubes it matches baseline grasp success at roughly half the grip force and cuts soft-object damage from $100\,\%$ to $40\,\%$.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.23972v1 Announce Type: new Abstract: Safety-aware motion planning remains a challenge in robotics, especially when missions are time-critical and are under complex specifications. In this paper, we propose safety-aware-stl-mppi, a computationally efficient sampling-based receding-horizon planning framework designed to promote satisfaction of constraints expressed in Signal Temporal Logic (STL). Our approach encodes discrete-time STL formulas into candidate time-varying control barrier functions (CBF), which are integrated into a model predictive path integral (MPPI) controller. Our method inherits the benefits of low computational cost from an efficiently parallelizable sampling based planner and utilizes CBF for constraints expressed in STL. We compare against several MPPI baselines using four artificial Mars Rover planning case studies with a diverse environment and cost setups, where we show our method consistently achieving high safety and efficiency. We show a quadcopter planning experiment with NVIDIA Isaac Lab.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.23887v1 Announce Type: new Abstract: Latent-conditioned adaptive policies can control robots across changing dynamics, but their learned latents remain internal representations of the policy rather than physical models that can be inspected, rolled out, or used by other control modules. This limits closed-loop analysis, diagnosis, and further improvement of a fixed policy. A direct mapping from latent to physical parameters is also under-specified, because multiple systems can induce similar closed-loop behavior. We therefore decode each operational latent into a distribution of quadrotor models using conditional flow matching. The decoded distribution enables two downstream uses without modifying the policy: online predictive tuning of a high-level controller around the fixed low-level policy, and robustness analysis under specified disturbances. Under perturbed actuator dynamics, decoded-model predictive tuning reduces position tracking RMSE by $23\%$ and heading RMSE by $45\%$ relative to fixed gains. Under Gaussian force disturbances, decoded-model ensembles closely predict the lateral tracking-error evolution. Together, these results show that control latents can be converted into physical model ensembles for tuning, robustness analysis, and diagnosis of frozen adaptive policies.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.23863v1 Announce Type: new Abstract: Robots are beginning to act on world-model predictions, yet reliability is still expressed through instantaneous, model-internal signals. DreamLedger instead treats reliability as a persistent deployment object: an execution-settled credit file recording how often consumed predictions are borne out, indexed by operating condition, region, and prediction horizon, and consulted before each use. Each consumed prediction is registered as a claim; attributable outcomes are settled against arriving reality at zero labeling cost, an attribution stage excludes measurement-contaminated outcomes, and a settlement-supervised head complements sparse bins. The resulting credit gates consumption: low-credit predictions shorten the dependent horizon or trigger additional observation; every reliance event remains auditable via dependency tickets and replayable logs. We evaluate DreamLedger in three simulated domains (indoor flight, tabletop manipulation, 2D navigation), via mounts on unmodified DreamerV3, TD-MPC2, and V-JEPA 2-AC, and on a real Franka manipulator. Claim failure is dose-monotone in all 12 held-out condition-horizon cells. Credit-gated planning reduces burned imagination (consumed claims that later fail to redeem) by 62% (95% CI 43-81%) versus blind consumption, with equal success and comparable collision rates. At matched risk targets, persistent books cut verification probes from 1.00 to 0.36/episode in manipulation, at success 0.94 versus 0.98; settlement-grounded calibration retains moderate, seed-consistent operating points unlike raw instantaneous gates. The same trust layer operates across decoder-, latent-, and token-space interfaces, including V-JEPA 2-AC settled on real robot frames. On hardware, settlement remains operational under real sensing and contact noise, a deployment failure loop is re-priced online, and all 1,062 registered spends replay from the audit logs.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.23839v1 Announce Type: new Abstract: Embodied Agents System (EAS) are increasingly deployed in open-world physical domains, where reliability directly dictates deployment quality and human-agent trust. However, existing evaluations rely on outcome-centric metrics as success rate or safety scores that collapse diverse execution trajectories into coarse scores, obscuring the dynamic processes underlying agent behavior. Therefore, they ignore a critical property of EAS -- which we define as the Resilience -- that reflects how EASs recover, stabilize, and extend under perturbations and across iterative updates. The lack of resilience is particularly critical in open-world environments due to continuous unexpected disruptions, thus directly affecting the quality of EAS deployment. To address this problem, we gain insight from the resilience-engineering concepts to EAS groundings and propose a novel resilience evaluation framework that can be flexibly applied to any EAS. Specifically, we define the first comprehensive resilience metrics suite for EASs system that exposes Rebound, Stability, and Graceful Extensibility across embodied tasks execution, providing a practical grounding for EAS resilience analysis. We further implement the resilience evaluation layer that transforms execution process into assessments for diagnosis and optimization. Across 400 household tasks with 10 EAS, we reveal the process-level distinction hidden by outcome metrics, including recovery cost differences among successful episodes ($\Delta C_{rec}=25.2$), increased instability and task-family degradation. Metrics-guided optimizations reduce recovery cost and increase stability, graceful extensibility completion, showing the diagnostic effect of resilience evaluation. Our results reveal a trade-off among resilience characteristics, suggesting that a resilient EAS construction should be configured according to deployment-specific requirements.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.23831v1 Announce Type: new Abstract: While reinforcement learning (RL) allows generalist robot policies to continually improve during deployment, the large model size of modern generalist policies, such as VLAs, poses a fundamental obstacle to effective RL improvement. In particular, their severe inference latency---which can lead to pauses or jerky movements---can alter the effective environment dynamics and, if not correctly accounted for, break the Markov assumption that RL relies on, causing standard RL algorithms to fail completely. In this work, we introduce a latency-aware framework, Asynchronous RL with Intermediate Information (ARLI), that enables RL-based improvement of generalist policies under inference delays. Our framework builds on asynchronous inference approaches, which interleave action generation with execution to hide latency, and addresses its incompatibility with RL by providing a low-latency RL policy design that maximizes reactivity within the inference window through two contributions: state augmentations that restore near-Markovian structure by incorporating committed actions and a mid-inference observation. We evaluate our approach across simulated and real-world manipulation tasks, and find that it enables effective finetuning under inference delays where standard RL fails entirely, even matching or exceeding the performance of standard RL in idealized no-latency settings.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.23650v1 Announce Type: new Abstract: The perception of 3D space by mobile robots is rapidly moving from flat metric grid representations to hybrid metric-semantic graphs built from human-interpretable concepts. While most approaches first build metric maps and then add semantic layers, we explore an alternative, concept-first architecture in which spatial understanding emerges from asynchronous concept agents that directly instantiate and manage semantic entities. Our robot employs two spatial concepts (room and door), implemented as autonomous processes within a cognitive distributed architecture. These concept agents cooperatively build a shared scene graph representation of indoor layouts through active exploration and incremental validation. The key architectural principle is hierarchical constraint propagation: Room instantiation provides geometric and semantic priors to guide and support door detection within wall boundaries. The resulting structure is maintained by a complementary functional principle based on prediction-matching loops. This approach is designed to yield an actionable, human-interpretable spatial representation without relying on any pre-existing global metric map, supporting scalable operation and persistent, task-relevant understanding in structured indoor environments.