THE NEXT THING, IN PERSPECTIVEIndependent AI news

The latest AI news, in focus.

Official announcements and industry reporting. Follow the timeline of AI.

Today's news

News feed
AI NEWS × FOXAIFind your next step

From the latest news to tools that work for you.

Explore AI tools

Discover AI tools

Swipe to explore →
AI ShortWriting & content

AIS ALERT MANAGEMENT AND SHARED PLATFORM, QUICK COMMAND FOR MULTIPLE SCENARIOS

AI HINT COMMAND分类推荐榜首Pricing unverifiedView details
MemoAIMusic & audio

MemoAI 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.

AI AUDIO TOOL分类推荐榜首Pricing unverifiedView details
JAXModels & infrastructure

JAX 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.

AI DEVELOPMENT PLATFORM分类推荐榜首Pricing unverifiedView details
Open DesignDesign & 3D

OpenDesign 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.

AI design tools分类推荐榜首Free entry availableView details
KiroCoding & development

Kiro 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.

AI programming tool分类推荐榜首Free entry availableView details
EvoMapAgents & automation

EvoMap 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Pricing unverifiedView details
FinBusiness & support

CLIENT-ORIENTED AI SMART BODY。

Customer serviceSmartClient services待评分 · 分类列表推荐Pricing unverifiedView details
闪剪Video & animation

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Pricing unverifiedView details
AssemblyAIMusic & audio

AssemblyAI is a speech AI platform for developers, offering pre-recorded, real-time, and short-form synchronous transcription APIs. It enables the building of voice-based applications by integrating capabilities such as speaker identification, emotion analysis, chapter and summary extraction, as well as speech agent functionality, dictation, and sensitive information processing.

AI AUDIO TOOL待评分 · 分类列表推荐Pricing unverifiedView details
Udacity AI学院Education & languages

Udacity AI Academy is the gateway to AI courses and learning paths, covering machine learning, deep learning, computer vision, natural language processing, and AI product management, with courses and project-based training available at both beginner and advanced levels.

AI learning website待评分 · 分类列表推荐Pricing unverifiedView details

AI, as it happens

2116 published stories
Research paper · 491 storiesClear filters ×
2026-11-17
Follow the timeline
13:00

Benchmarking LLM Inference on Desktop-Scale NVIDIA Grace Blackwell Clusters

arXiv:2611.20289v1 Announce Type: new Abstract: Two NVIDIA DGX Spark GB10 systems connect directly over 200 GbE to serve larger language models and increase inference capacity, but the benefits depend on how they are deployed. We benchmark 17 open-weight checkpoints spanning dense and mixture-of-experts architectures, 8B to 235B parameters and four weight precisions on one and two RDMA-connected systems. Using vLLM, we compare tensor parallelism (TP=2), pipeline parallelism (PP=2) and a two-replica baseline at concurrency 1 to 64, with three independent launches per configuration. TP=2 delivers a median 1.59x peak-throughput gain over one Spark, versus 1.39x for PP=2 and has higher throughput in 93 of 96 matched comparisons with separated 95% Welch intervals. It reduces unloaded inter-token latency to 0.52x to 0.73x of one Spark, whereas PP=2 provides little reduction. TP=2 also achieves the highest goodput under a strict 100 ms inter-token latency objective wherever both strategies are supported and the objective is met. For models fitting on one Spark, TP=2 generally favors low-concurrency serving, while replication offers higher throughput at high concurrency. One Spark uses less GPU energy per output token at matched concurrency. Across three precision ladders, NVFP4 reduces unloaded latency more than adding a second Spark at BF16. NCCL microbenchmarks and comparisons with an earlier TCP campaign suggest that collective communication overhead contributes to the advantage of TP=2. These results provide deployment guidance for desktop-scale inference.

Chips, GPUs & hardwareRead original
13:00

Can Agentic LLMs Write Task-Based Parallel Code? A Study of OpenMP Tasking, HPX, StarPU and TTG

arXiv:2611.19105v1 Announce Type: new Abstract: Task-based programming offers more expressive power than loop-level parallelism, but the runtimes providing it differ widely in API style, maturity, and the amount of public code to learn from. This paper asks how well LLM agents write C++ for four of them: OpenMP Tasking, HPX, StarPU, and TTG. Instead of single one-shot prompts, we use an agentic workflow in which the model edits files, compiles, and runs its kernels until it reproduces a reference output. Five locally hosted open-weight LLM implement seven HPC kernels, including matrix multiplication, Cholesky and LU factorization, in all four frameworks and a serial baseline to verify their understanding of the problem in general. Every kernel is evaluated independently for correctness at each concurrency level, strong scaling, and peak memory. Model capability dominates the outcome: three models produce correct, genuinely task-parallel kernels in 57-82% of the cases, while two models rarely compile their own code and almost never succeed. For the capable models, OpenMP Tasking and HPX are handled most reliably, StarPU is close behind, and TTG trails. The best generated GEMM and factorization kernels match or exceed the multithreaded OpenBLAS/LAPACK reference. However, correctness overstates parallel quality: several "parallel" kernels contain no parallelism at all; and serialized task graphs and unsuitable task granularity remain common.

Workflows & integrationsRead original
13:00

Coordinating Distributed AI Servers with Industrial Loads to Reduce Grid-Interconnection Needs

arXiv:2611.18951v1 Announce Type: new Abstract: We show that co-locating distributed AI servers with industrial demand and coordinating AI workloads with production loads can substantially reduce the additional grid interconnection that AI computing requires. Grid interconnection is increasingly constraining the expansion of large AI data centers. Factories already have grid connections sized for their peak production loads, and we propose hosting AI servers during production valleys. We formulate a joint optimization that sizes CPU and GPU servers, schedules deadline-constrained tasks, and routes tasks among factories, and use it to compare three factory-site architectures with new large data centers serving the same demand. Applying this framework to 31 Chinese manufacturing industries, we find that AI demand and production loads often do not peak together. As a result, AI servers placed at factories and scheduled according to production peaks need about 60% less additional interconnection capacity than new large data centers, and 98% less when tasks are routed among a group's factories.

Data centres & cloud computeRead original
13:00

Making Preemption Productive in Long-Output LLM Serving

arXiv:2611.20106v1 Announce Type: new Abstract: Reasoning LLMs generate long outputs whose key--value (KV) caches occupy GPU memory for minutes. When memory fills, the server preempts requests, and a preempted request can repeatedly lose and recover its state while producing little new output. We call this behavior KV thrashing. In certain cases, existing systems leave more than a fifth of requests stalled for over a minute. Because preemption cannot be avoided without delaying admission, we ask how to make it productive. We present Stint, a serving system that preserves a preempted request's work, bounds how long it waits, and gives it fresh output after it returns. Stint stores fixed-length KV snapshots in a contiguity-first CPU pool with an exact-extent allocator, and moves them with fused K/V gather/scatter kernels and double buffering. Age-based readmission brings stalled requests back, and protection gives them a turn of fresh decoding before another preemption. Remaining-length estimates from decoding hidden states guide victim selection. On olympiad-math replays with Qwen3-32B on H200 GPUs, no request pauses for more than 50 seconds under Stint and p99 time per output token falls by 50.7\% relative to recomputation in the same engine. The replay as a whole finishes 10.7\% sooner (12.0\% higher throughput), because the requests that baselines starve no longer finish last.

Chips, GPUs & hardwareRead original
13:00

ReMoVe: Refining a Video Model's Own Motion for Coherent Human Video Generation

arXiv:2611.18666v1 Announce Type: new Abstract: Video generation models have become increasingly capable of synthesizing realistic human motion, yet they often lose track of the very structure that makes the motion plausible. As generated human motion becomes more complex, videos can suffer from progressive body deformation and appearance drift across frames. Existing motion-controlled methods use explicit representations to stabilize generation, but typically rely on pre-defined motion sequences as references. This raises a fundamental question: if the base generator already produces a usable coarse motion, why replace it with an external one? ReMoVe answers this question by treating the coarse output as a motion hypothesis rather than a final result. ReMoVe recovers and refines the underlying motion, then renders the refined motion as 3D mesh and transfers facial appearance onto it, thereby improving motion accuracy and identity consistency. We further derive depth from the same 3D scene and camera trajectory to impose scene-level spatial consistency beyond the mesh. By jointly conditioning video generation models on mesh and depth, ReMoVe synthesizes high-quality motion videos with controllable camera trajectories and enhanced spatio-temporal consistency. Extensive experiments demonstrate that ReMoVe improves human structural stability, appearance consistency, temporal coherence, and motion-following fidelity, while retaining the base generator's motion prior and offering accurate camera control.

Video generationRead original
13:00

Supercharging Olmo-core for Efficient and Scalable MoE Training

arXiv:2611.18956v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models add parameters without proportionally increasing per-token compute. However, training cost also depends on bytes moved, memory held, and kernels launched, and many of those costs follow total parameter size rather than active compute. On infrastructure built for dense models, this mismatch is costly: in early baselines, throughput fell as stored expert parameter size grew, even though the useful work per token stayed nearly fixed. To close this gap, we present a redesigned training stack in Olmo-core, built for efficient, scalable MoE training. We replace the Fully Sharded Data Parallel (FSDP) of earlier Olmo-core versions with an architecture built on Distributed Data Parallel (DDP), and add Expert Parallelism (EP), Pipeline Parallelism (PP), a distributed optimizer, and activation recompute. We propose NVSHMEM-based rowwise EP, which writes each token directly into its expert's buffer, avoiding dispatch and combine permutation overhead. We make EP fully synchronization-free by keeping routing metadata on the GPU and using device-scheduled grouped GEMMs. Closely integrated MXFP8 cuts compute, activation-memory, and transport costs, and topology-agnostic checkpoints let the parallel layout change between runs. On NVL8 B300 nodes, the stack supports training configurations from 12.9 billion to 1.2 trillion total parameters on up to 512 GPUs, reaching 858 useful-model TFLOP/s/GPU at 1.2 trillion with MXFP8 and per-layer recompute; an experimental capacity test with the optional DeepEP v2 backend reaches 2.38 trillion. We also explain each design choice and share findings for other training systems; for example, we identify a failure pattern we call Token Gerrymandering, in which the MoE router can learn to hack the load-balancing loss, and find that overlapping communication with computation can slow the overlapped kernels by more than it hides.

Token pricing, cost & energyRead original
13:00

Thinking from Another Side of the Box: Spacetime Images for Computer Vision

arXiv:2611.18671v1 Announce Type: new Abstract: Computer vision methods for video understanding, such as object detection and tracking, inherit the way videos are captured and displayed: as successive frames processed sequentially. However, a video is an inhomogeneous 2D+time volume of pixels, named voxels, and frames are only one family of cuts through it. In this frame-based representation, static backgrounds introduce computational redundancy, and motion can only be understood across several frames. In this position paper, we study another family of cuts: spacetime images (STIs), obtained by sampling any set of pixels other than frames, for instance a line of pixels followed over time. Such images are familiar in narrow forms, from line-scan inspection and kymographs to spatiotemporal slices for motion analysis, but have received little attention as a general input representation for computer vision and are often limited to (x,t) or (y,t) cuts. We define new cuts leading to STIs in their general form, explain how to read their content, and show that a family of cuts tiles the video so that existing dense annotations transfer at no cost. We also detail how motion appears in an STI, spatially and in the frequency domain, and discuss applications such as walking pedestrians, deposited objects, and dynamic scenes. Two pilot experiments illustrate the representation. The first trains a segmentation network entirely in the spacetime domain, on transferred annotations, and performs background subtraction on CDnet 2014 close to supervised frame-based methods, without explicit temporal modeling. The second recovers the pan speed of a camera as a moving cut, identified by a simple criterion on the frequency spectrum of the resulting image, turning a temporal estimation problem into the choice of a cut. Our position is not that STIs should replace frames, but that slicing the video volume is a design variable worth studying in its own right.

Copyright, privacy & ethicsRead original
13:00

TileCache: Serving Multi-Round Diffusion Image Editing with Compressed Activation Caches

arXiv:2611.20246v1 Announce Type: new Abstract: Multi-round diffusion image editing can reduce computation by reusing intermediate activations, but retaining these activations across editing rounds introduces substantial memory and bandwidth overheads. Compression can reduce these overheads, but efficient cache construction is challenging: compressing only after editing requires buffering over 100 GB of activations per request. Moreover, the compressed cache must support selective reuse, as future masked edits require only a subset of the cached activations. It also exposes a scheduling challenge, as cached edits are faster than initial generations, causing naive policies to severely delay either initial generations or editing requests. In this paper, we aim to address both challenges through compression-informed serving. We develop TileCache, a serving system for multi-round diffusion editing. It compresses reusable activations and incorporates a scheduler that balances both edits and initial generation requests. Compared with the state-of-the-art image editing baseline, TileCache sustains over 2x the request arrival rate at 90% SLO attainment. It completes edits 2.4-4.5x and initial generations 1.3-2.2x faster than the baseline, while preserving image quality.

Image generationRead original
13:00

Two-Robot Evacuation from a Unit Disk in the Segment Visibility Model

arXiv:2611.19992v1 Announce Type: new Abstract: Under segment visibility, two robots discover a target as soon as it belongs to the segment joining their positions, even if neither robot has physically reached it. We study two unit-speed robots starting at the center of a unit disk that must both reach an exit (target) placed at an unknown point of its boundary. In our model robots are permitted to leave the disk while searching. We give a three-phase tangent-and-arc algorithm whose exact worst-case evacuation time is 2\sqrt{3}+\pi/3 \approx 4.511299$. We also prove a matching lower bound for the class of descending horizontal full-slice sweeps, allowing asymmetric robot trajectories. The proof uses an exterior path-length inequality and a feasible minimum-half-width symmetrization. Determining the optimal time over all segment-visibility algorithms remains open.

Copyright, privacy & ethicsRead original
13:00

UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models

arXiv:2611.18668v1 Announce Type: new Abstract: Unified multimodal models can support both visual understanding and generation, yet generative training does not necessarily improve understanding. We argue that this limitation may arise from a mismatch between the representation targeted by generation and the perceptual representation used for understanding. Conventional generation objectives primarily optimize synthesis-oriented spaces such as discrete visual codes or generative latents. We therefore introduce UMM-JEPA, which reformulates generation as progressive prediction of continuous visual-understanding representations. The model constructs a multi-scale representation hierarchy from coarse to fine, while pixel rendering is decoupled from representation pretraining and attached only afterward. Controlled comparisons show that the representation-prediction objective accounts for most of the understanding improvement, while a data-matched control leaves the group means nearly unchanged. UMM-JEPA reaches a 16-benchmark visual mean of 51.71, against 46.36 for the understanding-only Qwen-VL baseline, and the text mean also rises. Compared with discrete-code and latent-flow generation objectives, perceptual representation prediction yields stronger and more consistent transfer to understanding. Linear probes and visual-evidence interventions further reveal richer object and spatial structure and stronger use of image-specific information. These results suggest that generation can benefit understanding when it directly supervises the perceptual representations that understanding consumes.

Training, tuning & alignmentRead original
13:00

VidEngram: Agentic Long-Term Video Understanding via Structured Hierarchical Memory

arXiv:2611.18578v1 Announce Type: new Abstract: Long-video question answering is wasteful and lossy when a multimodal model must re-encode the same video for every query: context limits force sparse sampling or truncation, and no reusable representation remains for later questions. We present VidEngram, an agentic video QA system that builds a persistent hierarchical memory once at ingest and answers later questions from that memory. VidEngram captions video and audio jointly with Qwen2.5-Omni, consolidates segment memories into episode and entity layers, and uses a text-only agentic planner with specialized retrieval tools to produce grounded answers. The web interface makes this process inspectable: users can watch memory formation, inspect retrieval traces, verify cited evidence in the video player, and explore entity relationships. On the full OmniVideoBench, VidEngram with a GPT-5-mini planner outperforms a strong single-pass Qwen2.5-Omni baseline (37.0% vs. 32.3%), with gains concentrated on longer videos where single-pass coverage becomes sparse. Because perception is paid once, subsequent queries use low-cost text-only planning.

Model releases & updatesRead original
2026-11-16
Follow the timeline
13:00

AI-Voyager: A Public-Interest System for Human-AI Civic Reasoning to Contest and Shape the Rules That Govern AI

arXiv:2611.17564v1 Announce Type: new Abstract: Governments are writing rules for artificial intelligence that decide what counts as an automated decision or a harm, often before the people they affect have a chance to question them. We introduce AI-Voyager, a public-interest system for human-AI civic reasoning, in which people and AI work together to understand, contest and shape the rules that govern AI. A resident can find their city's rules on AI in hiring or upload their country's AI strategy, read it as an affected worker would, open the passage behind any answer, and draft a revision. Its architecture turns 3,653 governance documents from city, state, federal and national governments into passages that keep their page and edition, and retrieves evidence through bounded agentic search that verifies each statement. On 360 new questions that require finding the relevant documents, it reached 83.0% macro recall, against 80.5% for the strongest baseline, 73.7% without iterative search and 99.1% on a benchmark with fixed documents. In a study with 24 participants new to two AI bills, most proposed changes asked how provisions would apply. Participants chose lenses for the kind of explanation they wanted, and citations signaled grounding but rarely led them to check the source. By binding AI assistance to the exact text of public documents, this work introduces a grammar of operations and a design space that inform how such systems are designed and evaluated, and how people take part in governing AI.

Model evaluations & benchmarksRead original
13:00

An Operationalization of Opaque Serial Depth

arXiv:2611.17495v1 Announce Type: new Abstract: Chain-of-thought (CoT) is currently a valuable tool for overseeing AI models, but some architectural shifts could significantly reduce CoT monitorability. We operationalize a measure that serves as a proxy for the amount of unverbalized serial cognition a model can perform, as a specific instantiation of the notion of opaque serial depth: roughly, the length of the longest path through a model's computation that does not pass through an interpretable bottleneck. Our main contribution is a particular standard for what counts as such a bottleneck. We define natural-language-rooted (NL-rooted) nodes as nodes that were initialized from a pre-training prior to produce human-understandable outputs, whose output space has not been expanded beyond that prior, and whose outputs the model has not been modified to interpret as a different type of data. By construction, the resulting measure, NLS depth, can be adjudicated before training from an architecture, training recipe, and deployment configuration alone, and is insensitive to ordinary post-training such as prompting, distillation, and RL. We find that, across open-weight models, NLS depth correlates strongly with layer count, with some exceptions, and has grown slowly over recent years. It would likely grow slowly under continued scaling of standard transformers, while latent-reasoning architectures such as full-bandwidth transformers could increase it by a large amount. We work through how NLS depth applies to a range of existing and proposed architectures, discuss alternative operationalizations, and give a worked example bounding the depth of Gemma3-1B. We argue that AI developers should track and report the NLS depth of their models as a complement to direct measurements of CoT monitorability.

Training, tuning & alignmentRead original
13:00

Availability-Aware Historical Feedback Learning for Electric Arc Furnace Temperature and Chemical Composition Prediction

arXiv:2611.17463v1 Announce Type: new Abstract: Electric arc furnace (EAF) steelmaking plays an increasingly important role in recycled and lower-carbon steel production. However, variability in charged materials, energy input, and operating conditions makes accurate prediction of molten steel temperature and final chemical composition challenging. Intermittent or delayed measurements limit the information available for timely prediction. This study develops an availability-aware historical-feedback learning framework for predicting EAF endpoint temperature and the final concentrations of twelve chemical elements. Eight industrial data sources are integrated into three progressively enriched predictor representations comprising 19 static, 39 temporal, and 47 history-informed features. Historical outcomes are incorporated only when eligible under an assumed 60-minute measurement-release delay. Using 19,738 temperature heats and 3,341 chemistry heats, twelve tuned regression algorithms are evaluated through chronological forward validation. The proposed historical-feedback representation reduces root mean squared error (RMSE) in 147 of 156 matched algorithm-target comparisons. For temperature prediction, ExtraTrees achieves an RMSE of 12.290 degrees C, representing a 5.54 percent reduction compared with its temporal-only counterpart. Historical-feature ablation and feedback-delay sensitivity analyses demonstrate the importance of recent outcome information and its availability. In a separate retrospective later-period evaluation, lightweight adaptive residual correction reduces temperature RMSE from 12.502 to 12.275 degrees C without retraining the underlying model. Exploratory deep learning comparisons and target-specific feature-attribution analyses provide additional insights into predictive behavior. The results establish historical outcome availability and sequential feedback as important considerations for EAF endpoint prediction.

Model evaluations & benchmarksRead original
13:00

Benchmarks Don't Talk Back: Learning Through Self-Disagreement

arXiv:2611.17563v1 Announce Type: new Abstract: A benchmark usually measures a language model alone with a question, and deployment rarely looks like that: answers get contested, and models give up correct ones under counter-reasoning that is itself wrong. We show that what fails there is not a shortfall of accuracy but a capability in its own right -- knowing when to hold a position and when to yield to a better one -- which we call dialectical competence. It stands on first-answer accuracy without following from it: a model can be made materially better at answering and no better at this, and training for accuracy alone can drift against it. Nor can it be bought at inference, by self-reflection or by sampling more. Taking a cue from the dialectical tradition in philosophy, in which productive opposition arises within a position rather than being imposed on it from outside, we hypothesize that this capability can be trained from opposition the model supplies itself. It states a position, generates the strongest case against that position -- its antithesis -- rules on whether the case stands, and is trained on that ruling, with no second model at training or at deployment. We call this learning through Self-Disagreement: reinforcement learning from verifiable rewards throughout, where the same check that scores an answer against its reference scores the ruling too, so no reward model, no preference data and no human annotation enter anywhere. The capability is trained rather than elicited: weak in the base model, it arrives with the reward, is not paid for out of first-answer accuracy, and holds against challengers the model never trained against, including ones stronger than itself. The opposition a model needs in order to improve, it turns out, need not come from outside it.

Model evaluations & benchmarksRead original
13:00

CamSpokenNLI: A Pilot Resource for Cross-Variety Transfer Evaluation in Cameroon Pidgin English and Camfranglais

arXiv:2611.17573v1 Announce Type: new Abstract: Cameroon Pidgin English (a West African Pidgin English variety) and Camfranglais are widely used in Cameroon, yet to our knowledge, neither has a dedicated spoken Natural Language Inference (NLI) resource. We introduce CamSpokenNLI, a pilot dataset of 114 scenario-matched spoken NLI items in each variety (228 in total), recorded by one native speaker from Buea. Each item pairs premise audio and text with a hypothesis, an NLI label, and English glosses. The author assigned labels, so the dataset is an exploratory resource rather than a mature benchmark. The NLI experiments use the reference text; the audio is evaluated separately. XLM-RoBERTa baselines with five-fold item-level cross-validation reach 44.7% on Pidgin and 46.2% on Camfranglais (chance 33.3%). Still, neither is statistically distinguishable from hypothesis-only input, so hypothesis wording may account for much of the accuracy. Under disjoint-item cross-variety transfer, where a test item's counterpart is never seen in training, accuracy is 40.1% (Pidgin to Camfranglais) and 45.6% (Camfranglais to Pidgin). A counterpart-leak audit raises this to 60-64%, illustrating how counterpart leakage can overstate transfer. Zero-shot Whisper transcription of the recordings performs poorly: the best word error rates are 66.6% for Pidgin and 45.5% for Camfranglais, and with automatic language identification, Whisper Large-v3 labels 93 of 114 Pidgin recordings as Yoruba or Swahili. Together, the results suggest that such resources need disjoint-item evaluation and hypothesis-only controls, and that speech recognition must be adapted to these varieties before spoken NLI can be tested end to end.

Model evaluations & benchmarksRead original
13:00

Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent

arXiv:2611.17939v1 Announce Type: new Abstract: Can you trust a finance agent you did not build? We take the reference agent shipped with the Vals Finance Agent Benchmark v2, leave it untuned, and ask four questions a leaderboard score does not answer. Is the score stable? Seven identical runs on 18 questions pass between 105 and 123 of 149 rubric criteria, and the bill varies by up to 17%. When the agent fails, who owns the fix? We classify 20 failed trajectories, from three runs of nine held-out questions, by the layer whose owner would remedy them, under a taxonomy frozen in advance: 13 belong to the agent's instructions, 3 to its tools, 4 to the model, none to its data. Can that diagnosis be trusted? Four blind readers from three model families, given only the traces, name the same fault as our LLM analyzer in 94% of cases, the rate at which they agree with one another (93%). Can a change be trusted? An optimization loop reads the traces, makes one targeted change per round and keeps it only if it clears a fixed threshold. Under a cost objective its final configuration costs 0.34x the baseline on the held-out questions (95% CI [0.22, 0.58]) at accuracy within noise. Under an accuracy objective it gains 14 points on the development questions and 1.5 on the held-out ones (CI [-5.3, +7.2]). Judged against the measured run-to-run noise, under a rule written before the test was opened, the first is a real saving and the second is not. This is a case study of one agent and nine test questions, not a general result.

Model evaluations & benchmarksRead original
13:00

CarryOn: Learning What to Keep in Context for Long-Horizon LLM Agents

arXiv:2611.17808v1 Announce Type: new Abstract: Long-horizon LLM agents can coordinate tools and applications to complete complex, multi-step tasks. As their interaction histories grow, effective context management becomes essential for reliable and efficient execution. Existing methods reduce context through summarization, pruning, or history selection. However, shorter contexts do not necessarily support better decisions: summaries can omit exact details needed for later actions, while retaining entire interactions can carry substantial irrelevant information. We propose CarryOn, a lightweight context manager that pairs compact execution state with fine-grained, source-linked evidence. A learned selector and adaptive retention policy keep relevant evidence available without additional LLM calls for context management. We introduce two complementary evaluation metrics: $S_\alpha$ prioritizes task success while accounting for resource use, and normalized cost per success (NCS) measures the resources spent per successful task. Across AppWorld, OfficeBench, and Tau2 Telecom with three LLM Actors, CarryOn achieves 75.7% macro-averaged task success, exceeding the strongest baseline by 6.7 percentage points. It also achieves the best average scores on both metrics.

Model releases & updatesRead original
13:00

Creating Steering Vectors via Input Optimisation

arXiv:2611.17481v1 Announce Type: new Abstract: Activation steering influences a language model's behaviour by adding a steering vector to its residual stream during generation, but it requires white-box access to modify the hidden states at every generation step. We introduce ActGCG, a modification of Greedy Coordinate Gradient which optimises a suffix to match the target activations obtained by adding a steering vector to the residual stream. We further introduce universal suffixes trained across many prompts at once, a model-translation step that rewrites the suffix into human-readable text midway through optimisation, and a soft-suffix variant to remove the discrete token space constraint. We study two behaviours: steering a model to answer in German, and anti-refusal steering for jailbreaking. For German, a discrete suffix reproduces the steering vector's behaviour almost perfectly and transfers well across prompts and models. For anti-refusal, the equivalence is weaker, succeeding under a phrase-avoidance metric but only partially under the stricter HarmBench classifier. Our results show that a steering vector's behaviour is reachable from the input, with no access to model internals at generation time, up to a loss that depends on the concept being steered.

Model releases & updatesRead original
13:00

Creative Product Design under Brand Image Constraints

arXiv:2611.17762v1 Announce Type: new Abstract: Industrial design requires creative visual exploration while satisfying constraints that are often product-specific and implicit. Existing text-to-image (T2I) approaches can generate creative designs through concept blending or multi-agent self-enhancement, but they provide limited mechanisms for ensuring that generated designs remain consistent with such constraints. We focus on brand image as a representative design constraint and propose a framework for brand-aware redesign generation. Given a product name, the framework constructs a brand image survey report that summarizes product and market information, derives a creative direction from the report, and integrates this direction into a self-enhancement loop in which generated images are critiqued and prompts are revised. We evaluate the framework on 50 redesign tasks across five product categories, comparing it with Naive T2I, IP-Adapter/IT-Blender, and unconstrained self-enhancement under the same T2I backbone. By a VLM-as-Judge protocol to measure creativity and brand identifiability, the proposed framework achieves a more favorable trade-off between the two objectives, with particularly clear gains in highly constrained categories such as automotive and motorcycle, where the plausible design space is relatively limited compared with that of other product categories. These results suggest that dynamically eliciting and textualizing brand image can guide creative product design generation under brand image constraints.

Image generationRead original
Every update links back to its source.
STAY CURIOUS. STAY INFORMED.

Stay informed about the changes that matter.

Give your curiosity direction. Make every day of reading count.

Subscribe via RSS