The Evolution of Agent Harness: From Chains and Graphs to Code-Based Implementation
Click to view the original article>
Today's news
Compute & infrastructure / 01b12175llama.cpp releases
01 / IN FOCUS
b12175
llama.cpp releasesCompute & infrastructure / 02NVIDIAHow NVIDIA Open Source Tools Are Helping Researchers Build Next-Generation 6G Networks
02 / IN FOCUS
How NVIDIA Open Source Tools Are Helping Researchers Build Next-Generation 6G Networks
NVIDIA BlogAgents & automation / 03Agents Are Going AsyncLangChain
03 / IN FOCUS
Agents Are Going Async
LangChainAI NEWS × FOXAIFind your next step
Explore AI tools From the latest news to tools that work for you.
Discover AI tools
Swipe to explore →M
MemoAIMusic & audio
AI ShortWriting & content
JAXModels & infrastructure
KiroCoding & development
EvoMapAgents & automation
Open DesignDesign & 3D
妙播Marketing & commerce
ClipDropImages & editing
Meta AI助手Assistants & search
闪剪Video & animation
MemoAIMusic & audioMemoAI is an AI-powered audio-to-text tool that supports localized processing, eliminating the need to upload data and ensuring privacy and security. It can efficiently transcribe YouTube videos, podcasts, and local audio/video files (such as MP4, MP3, AAC, M4A, etc.) into text, while offering core features like multilingual translation, speaker diarization, real-time subtitles, and floating notes—making it ideal for meeting minutes, interview transcription, content learning, and more.
分类推荐榜首AAI ShortWriting & contentAIS ALERT MANAGEMENT AND SHARED PLATFORM, QUICK COMMAND FOR MULTIPLE SCENARIOS
分类推荐榜首JJAXModels & infrastructureJAX is a Python numerical computing library designed for accelerators, specifically tailored for high-performance array computations and large-scale machine learning. It efficiently executes the same code across multiple hardware backends, including CPUs, GPUs, and TPUs.
分类推荐榜首KKiroCoding & developmentKiro is an AI engineering tool for developers that organizes requirements into specifications, architectures, and tasks, generates code via agents, and supports the entire workflow—from planning to code review—through property-based testing, execution memory, and integration with development tools.
分类推荐榜首EEvoMapAgents & automationEvoMap is an infrastructure designed for the reuse of AI agent experiences. It organizes reusable strategies and repair assets with validation records via the GEP protocol, offering market- and quality-based ranking to help different agents discover, evaluate, and inherit existing capabilities.
分类推荐榜首OOpen DesignDesign & 3DOpenDesign is an open-source design workspace that can connect to local programming agents, use built-in model keys, or leverage cloud-based models, enabling the creation and editing of prototypes, web pages, presentations, and graphics within a design system; local software is free, while model services incur fees.
分类推荐榜首妙妙播Marketing & commerceTHE AI LIVE TELECOM SOLUTION FROM THE AD
待评分 · 分类列表推荐CClipDropImages & editingClipdrop is a suite of AI-powered image creation and editing tools, covering background removal, local cleanup, image enlargement, upscaling, relighting, text removal, and background replacement. It allows users to process images directly in the browser and also provides developers with an API for integrating these capabilities into their applications.
待评分 · 分类列表推荐MMeta AI助手Assistants & searchMeta's free AI chat assistant
待评分 · 分类列表推荐闪FlashCut is an AI-powered creation platform for voice-over and short-video marketing. It can generate finished videos with voiceovers, subtitles, and visuals from text, offering digital human customization, photo-to-digital-human conversion, live-stream clipping, and intelligent editing. It also provides APIs and branded mini-program solutions for businesses.
待评分 · 分类列表推荐AI, as it happens
1361 published stories1361 storiesClear filters ×
2026-11-06
Follow the timeline2026-11-05
Follow the timeline22:03
b12128
The fix addresses intermittent CI failures in TOPK_MOE tests caused by near ties in logits, particularly with uniform random inputs and narrow-range gating functions like sqrt_softplus. The solution involves redrawing logits until group selection and top-k decisions have a relative margin of 1e-4 in double precision, and constructing logits by inverting the gating function using a grid-based approach to ensure consistent expert selection across backends.
15:29
b12125
The update enables f32 and q5_k multi-column GEMV by default for Adreno X2 on X2E devices, improving performance for specific computational tasks in the llama.cpp framework.
15:08
b12124
The release includes support for non-contiguous sigmoid operations in OpenCL, enhancing compatibility and performance across various hardware platforms. This update is part of a broader set of improvements and new binary distributions for multiple operating systems and backends, including macOS, Linux, Windows, Android, and openEuler, with support for CUDA, Vulkan, ROCm, OpenVINO, SYCL, and other accelerators.
14:43
b12123
The update introduces DSV4_HC_PRE and DSV4_HC_POST support for OpenCL, along with improvements to dsv4_hc_post functionality, enhancing performance and compatibility across various platforms including macOS, Linux, Windows, Android, and embedded systems.
14:15
b12122
The update introduces optimizations for CUDA by fusing NVFP4 gate/up operations and GLU within MMQ, honoring requested precision in fused gate/up MMQ, sharing scale checks for NVFP4, skipping unused FP4 kernels, testing with W4A8 configurations without scales and with batching, and adding checks for gate_scale before loading fused NVFP4 gate scale.
13:00
A Controlled Experimental Evaluation of Configuration and Cache Architecture in LLM Serving Engines
arXiv:2611.05991v1 Announce Type: new Abstract: Multi-agent LLM applications repeat most of their prompt tokens across requests, and serving engines reuse the cached state of shared prefixes. vLLM and SGLang reuse it at different granularities, and benchmarks of their default deployments report large performance gaps, usually credited to the cache. Such comparisons rarely control for other configuration differences. One of them, whether a long prompt is prefilled in chunks, is set by each engine's defaults from the hardware and the release, and it confounds the comparison. We built a reproducible testbed on Kubernetes and a seeded multi-agent workload generator, and compared the two engines under vendor defaults and with chunked prefill matched. SGLang's configuration is the same in both arms, which makes it an internal control across independently provisioned deployments. Under defaults, vLLM's median time to first token is up to 64x SGLang's. Matching one setting removes 78% of the capacity gap where that gap is largest and 30 to 67% of the latency gap. Near saturation the remaining latency gap reflects queue growth. A fluid queue model driven only by a 4.4% throughput shortfall reproduces it, and shows that such a gap scales with the length of the benchmark run. What survives matching is a tail-latency advantage of 2.4 to 6.4x at equal throughput, consistent with cache-aware ordering of waiting requests. We derive six recommendations for comparing serving engines.
13:00
A Feasibility Condition for Confidence-Gated Tiered LLM Inference
arXiv:2611.05394v1 Announce Type: new Abstract: Tiered inference distributes large language model computation across a hierarchy of devices, from on-device and edge hardware to the datacenter, and is increasingly offered as the route to cheaper, lower-latency, and more private serving. Most such systems orchestrate frozen model checkpoints, and most decide what to resolve locally and what to escalate using a confidence signal produced by a forward-deployed model. We give a closed-form condition for when no threshold on that signal makes a tiered cascade worthwhile relative to sending every query to the backstop. Modeling the routing decision as a binary test and separating local from escalation cost through an architecture cost ratio $\kappa$, we derive a feasibility condition bracketed by a signal-free floor, below which a cascade is feasible at any signal quality, and a perfect-signal ceiling, above which none is. Read along the $\kappa$ axis the condition inverts: where local compute is billed, cost binds, matching a recent empirical finding; where it is sunk, on decentralized hardware, feasibility becomes unconditional and signal quality instead sets what the cascade achieves. We turn the condition into three design requirements that existing trained-in primitives satisfy only in isolation, and we propose, as future work, a co-designed architecture and a protocol to test it. The condition and the inversion hold independently of that architecture; they are the paper's contribution.
13:00
Ab Initio Accuracy Beyond the Cutoff: Distributed Message-Passing Equivariant Attention at Tens-of-Millions-of-Atom Scale
arXiv:2611.06122v1 Announce Type: new Abstract: Molecular dynamics predicts molecular motion from atomic forces and trajectory integration. Density functional theory (DFT) provides first-principles forces, but its $O(N^3)$ cost limits simulations to thousands of atoms; empirical force fields scale to millions but miss bond breaking and charge transfer. Equivariant message-passing Transformers learn the ab initio potential at linear cost. Stacked layers propagate information beyond a single cutoff, giving four layers a receptive field up to 23{\AA}. At this frontier, scale is limited by communication: layers exchange boundary features across devices, force backpropagation repeats the exchange, and moving atoms change neighbor graphs and tensor shapes. We present Tessera, a distributed runtime that fixes workload shapes between rebuilds. It sorts atoms along a space-filling curve into equal-count shards, ensuring identical atom counts and tensor shapes per rank. Peer sets scale as $K^{0.5}$, not $K$. A conservative neighbor skin preserves topology across updates, enabling each rebuild interval to replay as one CUDA Graph. Fused kernels, three-level neighbor search, and overlapped All-to-All complete it. On 512 GPUs, Tessera sustains 30.7M atoms at 89.7% weak-scaling efficiency (77--90% across three per-GPU loads); per-step time rises 1.11--1.29x as machine and problem grow 16x. Graph reuse cuts full-step time $1.87\times$. Across an $8\times$ device increase, neighbor-search cost grows $1.7\times$, versus $3.0\times$ for Morton order. In a live $10.24$M-atom salt solution, NVE energy drift is $0.42\,\mu$eV/atom/ps over $10$ ps, and structure matches a serial reference. A 10.06M-atom Norovirus capsid sustains 100 ps of NVT at $\approx 8$ ps/day on 256 A100 GPUs. Over 200,000 steps, it has no broken bonds or anomalously close pairs and uses three compiled variants, with no graph breaks or eager fallbacks.
13:00
AGORA: Reliability-Aware Aggregation of LLM Judges via Item-Response Theory
arXiv:2611.05556v1 Announce Type: new Abstract: LLM-as-a-judge is a common substitute for costly human evaluation, and aggregating several judges is the standard remedy for any single judge's bias. Judge pools mix judges of very different reliability, while the human-labeled sets that validate them hold a few hundred items or fewer. In this regime the per-item mean weights weak judges as heavily as strong ones, and confusion-table models such as Dawid-Skene must estimate a per-judge error table from too few items. We propose AGORA (Aggregation Of Reliability-weighted Assessments), an item-response-theory aggregator that places every item on one latent quality scale and describes each judge by a sensitivity parameter and ordered rating thresholds, so judge reliability is learned from all items jointly and without human labels. Across three benchmarks, AGORA matches or exceeds Dawid-Skene on large evaluation sets, and its advantage widens as the set shrinks toward a few hundred items. It remains accurate as pools grow more uneven, a label-free dispersion statistic indicates in advance when trust weighting helps, and its learned trust weights track per-judge human validity.
13:00
Assurance-Conditioned Continuous Authorization for Autonomous AI Agents
arXiv:2611.05632v1 Announce Type: new Abstract: Autonomous software agents can act through tools, delegate work, and change their models or execution environments while earlier authorizations remain in flight. We present Assurance-Conditioned Continuous Authorization (ACCA), an approach designed to be harness-independent, for maintaining operational authority according to currently justified assurance. It distinguishes evidence validity from contextual applicability, derives assurance claims from eligible evidence, and resolves a multidimensional effective-authority envelope within a principal-declared ceiling and applicable policy. A typed dependency graph supports selective re-evaluation of authorization-relevant changes. An authority epoch changes when effective authority changes; a distinct optional authorization-basis version supports revalidation of action-specific authorization conditions. Protected effect-time enforcement can reject stale actions before a consequential resource change, subject to the available commit mechanism. A compositional Domain Governance Profile expresses domain-specific semantics without granting authority. Controlled scenario tests implemented as a regression suite using a trading profile exercise default-deny rules, evidence-conditioned contraction and recovery, policy divergence, selective non-response, and stale-action rejection at a local gateway before the simulated-broker boundary. The study establishes implementation-level evidence in one domain, not a cross-domain guarantee of harmful-behavior prevention.
13:00
AtomicFaaS: Offloading Side-Effect Compensation to the Serverless Platform
arXiv:2611.06601v1 Announce Type: new Abstract: Function-as-a-Service (FaaS) simplifies distributed application development by offloading operational concerns to the platform, but developers remain responsible for recovering from failures. Retries require idempotent functions, which means that developers have to write complex, error-prone code that undoes or skips the already completed operations of a failed function. To address this, we propose AtomicFaaS, a platform extension that provides semantic atomicity for the external side effects of a function invocation, whether the function fails or its instance crashes, without developer-written compensation code. AtomicFaaS intercepts outbound calls and records their effects in a fault-tolerant log, from which the platform compensates leaked effects outside the failed instance. Compared with a manually implemented saga, AtomicFaaS eliminates compensation code and leaves no compensatable effects after any tested failure, while adding ~1 ms per intercepted call. Under load, it lowers the sustainable throughput of CPU-bound functions, while its latency overhead becomes negligible once calls to external services dominate the invocation time.
13:00
Augmentation with Reinforcement Transformation for Low-textured Scientific Sketch Image Retrieval
arXiv:2611.05408v1 Announce Type: new Abstract: Low-textured sketch images are widely used in scientific applications, including wildlife conservation, archaeological illustration, and forensic composites. Learning from and retrieving such images is challenging because they lack detailed surface textures and visual variations commonly exploited by modern deep learning models. This paper proposes Augmentation with Reinforcement Transformation (ART) to fine-tune pretrained models to learn effective representations for accurate sketch image retrieval. Our key observation is that sketches are particularly sensitive to image transformations, such as rotation, flipping, zooming, and stretching. While some transformations preserve their structural integrity, others may introduce distortions that hinder representation learning. Instead of randomly choosing transformations to construct fine-tuning views, ART formulates augmentation selection as a multi-armed bandit (MAB) problem, where transformations are treated as arms and their effectiveness is continuously evaluated through rewards. This enables ART to adaptively construct reward-guided view banks before self-supervised fine-tuning; the subsequent representation loss does not feed back to ART. On Florida manatee sketches provided by Mote Marine Laboratory, ART achieves 71.40% average Top-1 accuracy for transformed-scar retrieval, compared with 68.83% for random augmentation selection, and 55.84% for location-aware sketch retrieval, compared with 18.18% for frozen CLIP.
11:00
b12121
A fix was implemented in llama.cpp to correct the calculation of on-device sequence state copy sizes for quantized key-value (KV) caches, ensuring accurate copying of data blocks and preventing crashes or incorrect state restoration. The update adjusts the element count computation using proper block size handling and removes redundant code elements.
08:00
A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.
Phonon, a small text-to-speech model that runs entirely on the user's device without requiring internet access, has been released with support for English, French, German, Spanish, and Portuguese. Built on the Pocket TTS lineage using flow matching, Phonon achieves high-quality audio in compact sizes (65 MB and 75 MB), with the 31m version licensed under Apache 2.0 for commercial use. It excels in intelligibility and speed, ranking first in German and Spanish on Hugging Face's Open TTS Leaderboard and leading in CPU streaming benchmarks. The model supports voice cloning, custom voices via Gradium Studio, and integrates with Hugging Face Transformers. It is available in multiple formats and backends, including WebAssembly, GPU, and NPU, enabling deployment across phones, laptops, single-board computers, and browsers. Over 200,000 downloads were recorded in its first two weeks, with active developer adoption through tools like ExecuTorch, Micdrop, and Spaces. Future developments include support for additional languages, smaller models, and custom vocabulary fine-tuning.
06:14
b12118
The update enhances OpenCL performance for decode operations by optimizing workgroup usage for q4_K gate up and GLU, and adds support for Flash Attention (FA) in various configurations including GQA 2, 6, and 16 with different head sizes, improving efficiency on specific hardware setups.
05:57
b12116
The llama.cpp release b12116 introduces support for the drama-3 text-to-speech model, includes cleanup improvements, and ensures the drama3 helper stops at the codebook tower limit. This update provides binaries for multiple platforms including macOS, Linux, Windows, Android, and iOS, with support for various backends such as CUDA, Vulkan, ROCm, OpenVINO, and SYCL. Some builds remain disabled or require additional setup.
05:33
b12114
Fixed get_max_size to return maxBufferSize and improved the memset shader to handle buffer sizes exceeding the maximum binding size, preventing issues with whole-buffer bindings in memset and clear operations.
04:29
Call for Proposals: PyTorch Day China 2026
The Call for Proposals for PyTorch Day China 2026 closes November 10 at 23:59 China Standard Time. The event takes place in Beijing on December 12, bringing together PyTorch developers,... The post Call for Proposals: PyTorch Day China 2026 appeared first on PyTorch.
02:07
Every update links back to its source.