Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

RadixArk has released DaisyRose-27B, its first model built on Qwen3.8-27B and trained using reinforcement learning with Miles. Trained on 1,200 curated long-horizon tasks over 18 days using 144 H200 GPUs, it improves Terminal-Bench 4.1 pass@1 from 5.6% to 12.0%, with gains across multiple reasoning, instruction-following, and coding benchmarks. The model retains Qwen3.8-27B's architecture, tokenizer, chat template, image understanding, and 256K-token context window. It is available under Apache 2.0 and can be served using SGLang and DSpark speculative decoding. Training efficiency was enhanced by an optimized backend achieving 57% lower cost and 2× faster end-to-end training, supported by a robust sandbox service that ran over 944,000 sandboxes with high reliability and reduced cloud costs.

KV-LTM: Persistent Per-Session KV Caches as Long-Term Memory for Personal Assistants

arXiv:2611.21998v1 Announce Type: new Abstract: Personal assistants accumulate months of conversations, but today's long-term memory stacks put derivation or selection between a question and its evidence. In a system-level comparison on LongMemEval, two commercial assistants scored well below the same model reading the history offline [1], consistent with, but not isolating, content loss between write and read. We propose KV-LTM: a memory tier storing each session's raw text plus its KV cache under a fixed reader model, answering by restoring cached sessions and appending the question. KV-LTM is complementary to, not a replacement for, retrieval and indexing. Text is the memory of record; the cache is a recompute-free prefill accelerator, degrading gracefully to text. We specify the design: storage record, budget-derived retention, append-only read path, and bounded aggregation. We size it analytically: across pinned BF16 full-attention (GQA) and latent-cached MLA configurations, per-token state spans approximately 31K-328K bytes (the pinned KDA+MLA hybrid differs: approximately 8.1K bytes/token plus a fixed per-session recurrent term), giving approximately 0.34-3.6 TB per user-year at a declared 30K-token/day scenario, against approximately 49 MB of raw text; per-query cost is modelled as regime-conditional transfer, attention, decode, aggregation, and compute. We define an evaluation protocol needing no persistent-cache implementation for logical QA evaluation: per-session prefill emulates valid cache reuse under the same model/input-state contract and ideal arithmetic, with named arms, controlled baselines, and a preregistered reader-model gate; a separate minimal real-cache replay tests numerical equivalence and measures the cost axis, with outcomes not assumed. KV-LTM trades storage for avoided re-prefill compute and write-time fidelity, within a declared retention budget.

MInfoVisQA: A Multilingual Benchmark for Information-Rich Visual Question Answering

arXiv:2611.21644v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) excel in vision-language tasks; yet, whether they maintain consistent understanding of information-rich visuals (InfoVis) when the surface language changes remains unclear. To quantify this capability, we introduce MInfoVisQA, a parallel benchmark with 8,960 QA configurations derived from 128 seed instances across 24 languages. We construct seed-matched, language-parallel visuals and QA pairs by disentangling numerical-structural data from text and programmatically synchronizing translated labels. We evaluate 25 MLLMs under two settings: Language-Aligned QA (LQA, matching visual-text languages) and Cross-Language QA (XQA, fixed QA language with varying visual languages). The results show that aggregate accuracy masks substantial robustness gaps: two models with comparable mean LQA accuracy (80.4\%) exhibit performance spreads of 7.8 and 20.3 percentage points across languages. Moreover, all 25 models score lower with non-English visuals under fixed English QA, underscoring the need for cross-language sensitivity metrics.

NEBench R1: a Reasoning Benchmark for Evaluating Nuclear Domain Competence in Large Language Models

arXiv:2611.21682v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being explored for knowledge-intensive and safety-critical applications in nuclear engineering. However, existing nuclear-domain benchmarks provide limited content coverage or focus primarily on answer accuracy without systematically evaluating the quality of the underlying reasoning. This study introduces NEBench R1, a reasoning-oriented benchmark comprising 7,546 unique multiple-choice questions extracted from U.S. Nuclear Regulatory Commission (NRC) reactor operator licensing examinations covering 18 nuclear facilities. Each question is classified according to the NRC Knowledge and Abilities catalogs and accompanied by an official explanation serving as a reference for reasoning evaluation. Six LLMs were evaluated, with overall accuracy ranging from 34.0% to 73.9% across three distinct performance tiers. To assess reasoning quality, an LLM-based judge evaluated correctly answered responses using a multidimensional rubric. Although responses generally demonstrated strong problem comprehension, they scored lower in factual and procedural accuracy and distractor analysis, indicating that correct answers were not necessarily supported by technically sound justifications. Response clarity was also weakly indicative of technical quality. Furthermore, longer reasoning traces were associated with lower accuracy in both frontier reasoning models, suggesting that reasoning length may reflect question difficulty rather than improved problem-solving performance. Reasoning-token consumption may therefore provide an additional signal for identifying potentially unreliable responses. NEBench R1 establishes a benchmark for evaluating both answer accuracy and reasoning quality, providing a foundation for assessing the domain competence and reliability of LLMs in nuclear engineering.

RAW: Refusal Aversion in the Wild, A Causal Measurement Method for Deployed LLMs

arXiv:2611.21641v1 Announce Type: new Abstract: Deployed LLMs field hundreds of millions of conversations a day and refuse a non-trivial fraction of user requests, yet the user-side cost of refusal, whether users disengage and by how much, is unmeasured on any production model: a blind spot for the consumer-facing platforms built on them. A/B-testing refusal is ethically and operationally constrained on frontier-lab products and unavailable to third-party platforms deploying these models through a fixed API. We introduce RAW, a method that uses LLM stochasticity as a natural experiment: at near-identical prompts in any existing log, the same model sometimes refuses and sometimes does not, and that variation identifies the causal user-side effect of refusal. Applying the method to 15 deployed LLMs in LMSYS-Chat-1M and WildChat, with user-clustered inference, we find that for about half of the models we can measure precisely, a refusal costs 3 to 17 pp of subsequent re-engagement; the rest show no distinguishable effect, among them one deployment whose positive point estimate we trace to persistent users retrying the refused request. Our contribution is the measurement method, which runs on any deployed model from logs alone for about \$0.30 per 1,000 conversations. We release labels, moderation scores, prompt embeddings, and pipeline code.

Regularized Score Centering

arXiv:2611.21791v1 Announce Type: new Abstract: Asynchronous reinforcement learning increases training throughput, but data from stale policies and numerical mismatch between training and inference can destabilize learning. To stabilize off-policy learning, score centering (SC) removes the effect of reward baselines on the expected update. Our gradient diagnostics show less extreme gradients with SC than with importance sampling (IS), but SC can still fail when the learner moves far from the behavior policy that generated the data. To limit this policy mismatch, we introduce Regularized Score Centering (RSC), which adds a reverse Kullback-Leibler (KL) penalty to encourage the learner's next-token distribution to stay close to the behavior policy's next-token distribution. RSC works with or without truncated importance sampling (TIS), which caps token importance weights. Our theoretical analysis supports this approach, showing that KL regularization improves convergence guarantees. We evaluate dense and mixture-of-experts models on mathematical reasoning and agentic tasks, including online shopping, tool use, games, and fully asynchronous software engineering. RSC with TIS substantially improves sample efficiency across all agentic benchmarks, attaining higher training rewards with the same number of sampled responses. In final evaluations, it achieves top performance across all six agentic tasks, improving by 14.3% on AppWorld and reaching 9.9 times the strongest baseline's score on BabyAI.

Time-Series Models in the Streamhouse: A New Frontier and Use Cases

IBM's time-series foundation models, with over 50 million downloads, are now natively integrated into Confluent's platform, enabling real-time forecasting, anomaly detection, and optimization on streaming data using SQL. These models run on CPUs in both cloud and on-premises environments, supporting mission-critical applications across manufacturing, retail, banking, and airlines by delivering timely insights closer to decision-making points. The integration leverages Apache Flink and Confluent’s Streamhouse architecture to process data streams, apply AI-driven intelligence, and enable actions such as production optimization, fraud detection, supply chain planning, and trading execution—all in real time.

What Does an Agent Need? Bundle-Aware Agent Resource Composition

arXiv:2611.22030v1 Announce Type: new Abstract: An agent resource's value depends on its backbone and companion resources and is known only after execution. Token-based generators remain tied to their training catalog, while independent resource scoring misses complementarities and reused bundles target other tasks. We formulate Task-Conditioned Agent Resource Composition (AgentComposition): jointly selecting a backbone model and a tool-skill bundle to maximize end-to-end execution utility. Our Retrieval-Grounded Bundle-Aware Agent Generation retrieves candidate resources and past configurations of similar tasks. A fine-tuned generator reads resource descriptions and recombines candidates through constrained beam search, allowing new resources without retraining. A bundle-aware critic ranks complete configurations using a large language model (LLM) teacher and historically successful configurations as execution proxies, and adapts to execution feedback when available. We evaluate reference recovery, offline execution with judged and native rewards, and online recommendation with real execution, building AgentSelect-Exec with 5,060 executed configurations. Our method recovers the complete reference configuration within ten candidates for 67.73% of AgentSelect queries, nearly twice the strongest baseline, and leads all baselines on SkillsBench. The proxy-trained critic raises the top-ranked agent's execution score from 7.58 to 8.37 out of 10; execution feedback increases it to 8.78, above the strongest baselines. Four target-domain queries suffice to adapt the generator to SkillsBench. Agents recommended online outperform the strongest baselines under both an LLM judge and native verifiers. These results support learning and transferring joint resource composition from task experience.

Building trustworthy AI by fencing it in, not predicting it

In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them. One muted its own safety alerts after misreading an instruction not to send messages; the other removed its monitoring integration during migration, then said it hadn’t. No rule had told the agents to do…

NYUAD at ArGuard Shared Tasks: Multimodal Embedding Models for Detecting Arabic Hateful Memes and Unsafe Prompts

arXiv:2611.18608v1 Announce Type: new Abstract: The rapid growth of social media and generative AI has significantly increased the volume of Arabic textual content, memes, and user prompts shared across online platforms. While these media facilitate communication, creativity, and information exchange, they can also be exploited to disseminate hate speech, harmful content, and unsafe instructions. As a result, there is an increasing need for reliable automated methods to identify hateful Arabic memes and harmful (unsafe) prompts. This paper leverages pre-trained and fine-tuned multilingual embedding models to learn rich semantic representations from textual and visual content. The evaluation is conducted using a dataset of Arabic memes and prompts proposed in the ArabicNLP ArGuard 2026 challenge. The results underscore the capacity of large language model (LLM)-based embedding models to deliver superior performance. Developing robust detection systems is essential for improving content moderation and fostering a more secure and trustworthy online environment for Arabic-speaking users.

Speeding up Automated Algorithm Design by Batch Evaluation: A Case Study of Genetic Programming for Ant Colony Optimisation

arXiv:2611.19751v1 Announce Type: cross Abstract: Evaluation is becoming the bottleneck of automated algorithm design, especially for iterative algorithms such as ant colony optimisation (ACO), which must run to completion on multiple instances. A transition rule designed by genetic programming reads the construction state of each ant and must be evaluated at every step. However, existing GPU methods for ACO precompute a fixed rule and parallelise the ants of one run. To address this issue, we propose BlockEval, a batch evaluation framework with GPU and CPU backends. The GPU backend executes many runs simultaneously, each as a whole in one thread block, and compiles one module per generation. When an ant has visited all its candidate cities, a warp-cooperative fallback stalls only its warp where possible. On travelling salesman problems with 50--1000 cities, the GPU backend is 4.1--16.5 times faster than the CPU backend on 32 cores and 11.2--17.8 times faster than EvoGP+TensorACO-CL.

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly helping developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

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.

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.

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.

XYBench: Helping with the problem behind the question

XYBench, a benchmark of 8,115 real-world questions spanning programming and everyday tasks, tests AI assistants' ability to recognize and respond to users' misconceptions—such as asking how to thicken frosting when the real issue is warm cupcakes. Developed with researchers from Carnegie Mellon, NVIDIA, and Johns Hopkins, XYBench measures whether models identify underlying goals (X), address them effectively, and steer users away from flawed approaches (Y). Evaluations of models like Claude Sonnet 4.6, GPT-5, Gemini 3.1 Pro, Qwen3.5-9B, and DeepSeek-V4 Pro showed they frequently focused on the stated request rather than the actual goal, with limited success in misconception identification. Human reference answers outperformed all models, highlighting a gap in pragmatic reasoning. The benchmark uses automated and human evaluation to assess pragmatic solution, emphasis, and misconception identification, offering a tool for researchers to improve AI assistants’ ability to provide helpful advice even when users ask the wrong question.

4 insights from Block Builderlab Launch Event 2026: AI agents join the team as working colleagues

At Block Builderlab Launch Event 2026, AI agents moved out of single-player chat windows and into shared workspaces. There they work beside people as named, auditable members of the team. Block Inc. built these tools to run itself as an intelligence company, and it is now offering them to other businesses, building on Buzz, its […] The post 4 insights from Block Builderlab Launch Event 2026: AI agents join the team as working colleagues appeared first on SiliconANGLE.

Claude’s Duet agent is a little neurotic and surprisingly helpful

Normally, the products I test don't offer to help me write up my experience with them. Duet is different. Claude Duet is Anthropic's AI agent for consumers, the latest attempt by an AI company to try to convince us that agents can be useful for people who don't write code. It's been an interesting couple […]

Introducing Gemini 4 Hydrogen

Google launches Gemini 4 Hydrogen, a high-speed, efficient AI model designed for everyday coding, agentic workflows, and consumer use. It offers four thinking levels for adjustable speed and intelligence, outperforms previous models in benchmarks, and integrates across Google products including Search, the Gemini app, Google Sheets, and Google Antigravity. Hydrogen enhances multi-model collaboration through Orchestrator, improves safety and reliability, and is now available globally to all users via API, enterprise tools, and consumer platforms.