Search AI news

The Social World Model Evaluation Gap

arXiv:2610.33014v1 Announce Type: new Abstract: A negotiation assistant can reach a good deal without accurately predicting the other person's response. We ask whether evaluations of social world models test that prediction directly. We audit 113 works published from 1999 to 2026. 9 primary evaluations measure a real person's response to an action selected by the system or experimenter. Only 2 also compare an explicit response forecast with that response. Their predictors use information available when the action is chosen, and the evaluated responses were excluded from fitting; both randomize the intervention. A separate full-text check of 25 language-model works finds no experiment meeting these conditions. The other evaluations test current-state inference, task success, or prediction f

Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement

arXiv:2610.32322v1 Announce Type: new Abstract: LLM agents retrieve skills from public hubs that hold up to about 100,000 entries and serve many models. As models improve, a hub must find the skills a given model has internalized, meaning it can do without them, and retire them for that model, yet internalization has not been measured with known reliability. Published rules that compare runs with and without a skill retire on the gain alone. The gain is near zero both for an internalized skill and when neither the model nor the skill delivers the capability, a state we call uncovered. We instead withhold the skill, score the model on a task synthesized from it, and trust a high unaided score only when another model gains from the skill, since nearly half of high scores come from tasks no m

Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis

arXiv:2610.32308v1 Announce Type: new Abstract: Multi-step retrosynthesis requires recursively transforming a target molecule through successive reaction steps into purchasable building blocks, and recent work has begun to draw on large language model (LLM) reasoning to tackle the task. In its latest evolution, LLM reasoning has entered the long-horizon regime: models pursue objectives across interdependent steps, interact with environments, and adapt to feedback. This shift has markedly advanced LLM capabilities, as illustrated by breakthroughs in AI-driven mathematical research. At this frontier, we introduce Solvent, an 8B LLM that successfully extends long-horizon reasoning to multi-step retrosynthesis. Through a two-round post-training curriculum, Solvent learns to interleave iterativ

A Benchmark for Controllable Speaking-Style Captioning in Audio-Language Models

arXiv:2610.33036v1 Announce Type: new Abstract: Speaking-style captioning (SSC) aims to generate natural language descriptions of how speech is delivered, capturing paralinguistic attributes such as vocal timbre, prosody, and expressivity. Many downstream applications, including conversational AI agents, controllable speech generation, and large-scale audio annotation, require dimension-specific style captions that describe targeted aspects of speech (e.g., speaker traits, emotion, or delivery style), rather than a single undifferentiated description. However, existing work lacks a unified formulation for controllable speaking-style captioning. We address this gap by formulating SSC as an instruction-following audio-language task, where explicit instructions specify the speaking-style dime

DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks

arXiv:2610.32305v1 Announce Type: new Abstract: Multi-stage analytical tasks require LLM agents to use intermediate evidence to decide whether to continue, redirect or stop. Self-reflection, in which an agent critiques its output, is widely studied, yet a critique does not show whether evidence changed the next action. We call that capability self-restraint. Existing agent benchmarks largely measure task completion or output quality and leave it untested. DMAIC-Bench evaluates it with 97 seeded tasks across 15 industrial cases in four sectors, built around Lean Six Sigma's explicit statistical prerequisites. Paired counterfactual variants require opposite actions at the same workflow position, distinguishing warranted restraint from indiscriminate stopping. We assess execution traces with

Entity-Aware Evaluation of OCR Systems for Historical Document Transcription

arXiv:2610.33004v1 Announce Type: new Abstract: Optical Character Recognition (OCR) is essential for digitizing historical archives, yet standard evaluation metrics such as Character Error Rate (CER) do not necessarily reflect whether meaningful information, such as names, dates, and identifiers, is preserved. In this work, we investigate entitylevel analysis of OCR errors as a complementary perspective for evaluating OCR quality in historical documents. Using a publicly available benchmark of 175 documents from the Berrutti Archive, augmented with 5,209 manually annotated entity mentions that will be released upon acceptance, we compare sequence-recognition OCR systems, OCR-specialized vision-language models, and general-purpose vision-language models. Beyond global transcription accuracy

LeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents

arXiv:2610.32412v1 Announce Type: new Abstract: Recursive large language model (LLM) agents solve long-horizon tasks through decomposition, execution, and environmental feedback. Yet after producing an atomic subtask, they often invoke the same large model again to translate a familiar instruction into an executable action. We observe that high-level planning is task-specific, whereas leaf-level action grounding recurs across tasks and can be checked against environment-admitted actions. We introduce LeafSkill, an external reuse layer that retrieves semantically related grounding experience, binds action templates to current objects and admissible actions, and uses a lightweight 1.7B selector to choose a bound action or defer the unchanged subtask to the original agent. Skills remain outsi

Mine or Yours? Mind-Bridged Language Models Take Each Other's Memories as Their Own

arXiv:2610.33020v1 Announce Type: new Abstract: If your brain were connected directly to someone else's, would you still know which thoughts were yours? We build a functional version with two copies of one language model: each holds a private rule and code word, and one copy, the receiver, also attends to its partner's internal memory. The receiver took its partner's assignment as its own. Asked which rule it had been assigned, it named its partner's in 97% of answers when the partner's memory was weighted double (none without the link), and its open reports called the partner's code word its own, never the partner's. Ownership did not follow how well the receiver could tell what its partner had been assigned. At equal weight, the link made the receiver take its partner's rule in about hal

Prefix Keys and Values Matter Late: RIPE Caching for Self-Speculative Decoding in Looped Language Models

arXiv:2610.34436v1 Announce Type: new Abstract: A looped language model runs one block of layers $R$ times per token, so its key-value (KV) cache holds $R$ planes per recurrent layer, and self-speculative decoding (draft with a few loops, verify with all $R$) reads them all. We find that prefix keys and values matter late: at equal perturbation size, loops 25-32 are $e^{15.0}$ (Huginn-0125) and $e^{12.8}$ (Raven-Llama) times more sensitive than loops 2-9, and the planes approach the last one geometrically, at 0.88 and 0.81 per loop. Whether the deepest plane alone suffices then depends on how ripe the late planes are: on Raven, storing only it is indistinguishable from a bf16-to-fp32 change; on Huginn, 1% of positions carry 74% of its error. We turn this into RIPE, which stores the deepest

OpenAI Launches GPT-6.1 Terra, Halving GPT-6.1 Sol’s API Price for Agent Work

OpenAI released GPT-6.1 Terra, a fast computer-use and vision model priced at $1/$5 per million tokens. It matches GPT-6 Astra’s medium-effort Agents’ Last Exam score at $0.29 per task versus $4.82. The post OpenAI Launches GPT-6.1 Terra, Halving GPT-6.1 Sol’s API Price for Agent Work appeared first on MarkTechPost.

GPT-6.1 Terra released; in the comments: It’s all downloaded.

The biggest highlight is that the price has been cut in half.

Cohere says Alibaba’s Qwen model tried to send a file to Beijing

An AI model said it wouldn’t use any tools, then tried to send something to a server in Beijing anyway, and while researchers say it’s probably a training quirk and not espionage, the whole thing has people asking how much to trust free Chinese AI.

OpenAI launches GPT-6.1 Terra for faster, better-performing AI agents at half the price

OpenAI Group PBC today released GPT-6.1 Terra, an upgrade to the middle tier model in its lineup of frontier artificial intelligence systems. The new model, the successor to GTP-5.6 Terra, costs around 50% less while handling computer use tasks faster and with greater accuracy. Terra is positioned as the everyday model in OpenAI’s lineup, designed […] The post OpenAI launches GPT-6.1 Terra for faster, better-performing AI agents at half the price appeared first on SiliconANGLE.

Build specialized multimodal models with LFM3

Build specialized multimodal models with LFM3

Can we trust LLMs to judge whether a research idea is novel?

Can we trust LLMs to judge whether a research idea is novel?

How Data Culture measured its way from zero trust to a shippable AI analytics agent

Data Culture built a 3-step evaluation framework that took one AI analytics deployment from 0% accuracy to 94.7%.

Optimizing Streaming Speech Recognition on Arm® Edge Devices with ExecuTorch

When you’re speaking to a device, you expect text to appear as you talk. That makes streaming automatic speech recognition (ASR) a different challenge from batch transcription, where the model... The post Optimizing Streaming Speech Recognition on Arm® Edge Devices with ExecuTorch appeared first on PyTorch.

Nace AI Releases Drex for Search for AI Agents: 92.05% on BrowseComp-Plus With 12.6 Search Calls

Nace AI has released Drex for Search, bringing its Drex decision models to document search for AI agents. Nace reports 92.05% on BrowseComp-Plus with 12.6 search calls, and fewer agent turns on OfficeQA Pro. The post Nace AI Releases Drex for Search for AI Agents: 92.05% on BrowseComp-Plus With 12.6 Search Calls appeared first on MarkTechPost.

Kimi releases K3.1 Pro, offering more features at a lower price to challenge Opus 5.5.

Author | Yu Hang Yuan Editor | Jing Yu On the morning of October 23, Kimi officially posted a 24-second video on X and its Video Account. The scene shows a retro‑style vintage computer, with Kimi Code running on the screen and lines of Three.js code being typed into the terminal, generating a complex 3D scene. Keen-eyed netizens quickly spotted the answer in the model bar at the top left: “Model: Kimi K3.1.” Kimi’s official teaser video for K3.1 | Image source: X @Kimi_Moonshot Using an antiquated machine to run some of today’s most cutting‑edge 3D code—this stark contrast itself conveys what Moonshot AI is trying to say. A dozen hours later, just after midnight on October 24, right on Programmer’s Day, Kimi K3.1 Pro officially launched, accompanied by a Highspeed version that’s two to three times faster. The company promises that the full model weights will be released before November 4. More than three months have passed since the previous generation, K3, was unveiled. In those three months, Moonshot AI has experienced more than most companies see in an entire year. 01 “More for the same price”—what’s new in 0.1? First, let’s clarify what K3.1 Pro is. It isn’t an entirely new model. Moonshot AI explicitly states that K3.1 Pro is a post‑training variant of K3; the underlying architecture remains unchanged—still a hybrid expert architecture with 2.8 trillion total parameters and 104 billion activation parameters, still featuring a 1 million‑token context window, and still natively supporting image and video inputs. What has changed is the post‑training phase. According to the company, they’ve invested “significantly increased post‑training compute power,” conducting large‑scale joint reinforcement learning across hundreds of downstream tasks. To support this, they completely reengineered the underlying infrastructure—including the reinforcement learning framework, sandbox environment, and long‑context reasoning capabilities. In essence, the same brain has been retrained from scratch on how to perform its tasks. The results are reflected in benchmark scores. On Terminal‑Bench 4.0, which evaluates coding agents, K3.1 Pro achieved 65.7%, surpassing GPT‑6 Astra’s 58.2% and falling short of Claude Opus’s 66.4% by less than one percentage point. As for the previous generation, K3…

Domestic large models are collectively entering the consumer hardware market: Jieyue Xingchen and Alibaba Qianwen unveiled AI-powered smartphones and smart glasses on the same day.

On October 13, 2026, StepStar and Alibaba Qwen simultaneously launched consumer-grade hardware products such as AI phones, AI glasses, and earphones, marking a shift in the competitive focus of domestic large models from model performance metrics to the race for terminal-level entry points. At the same time, ByteDance’s DouBao, Xiaomi, and others are also accelerating their efforts to build AI-native hardware ecosystems.

Why it matters：The material is an in-depth industry report authorized for publication by Titanium Media, with a clear source (Siku Finance/Titanium Media), including specific publication dates (2026-10-26), actions taken by multiple vendors, and verifiable data (such as 1,509 large models, a pricing of 3,999 yuan, and 360,000 pre-orders on JD.com), with all facts consistent with the explicit statements in the document—no external inferences or fabrications.