Search AI news

Decision Context: Persistent Behavioral Learning for AI Agents

arXiv:2611.08644v1 Announce Type: new Abstract: LLM agents do not learn from corrections across sessions. A user fixes the same mistake at the start of every conversation. Existing agent memory systems primarily handle facts, such as preferences, entities, and conversational history, rather than procedural knowledge. We present Forge Decision Context (forge_dc), a system that captures behavioral signals from human corrections and self-assessed tool-call failures, compiles them into imperative RULE directives, and injects them at the decision points where they apply. We evaluate forge_dc alongside four predecessor approaches on DC-Bench, a new benchmark of 71 scenarios across nine behavioral dimensions, built from real executed agent traces in a deterministic mocked-tool environment. forge_dc reaches 95% compliance, up from 55% with naive retrieval, while injecting approximately 10 times fewer tokens per query. Across the five-stage progression, the strongest systems represent behavioral memory as explicit directives and deliver it at the decision points where it applies. The results identify representation, activation, and placement as central design choices for persistent behavioral learning.

Zyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1.76x Faster

Zyphra released ZYFA, open-source FP8 and BF16 prefill attention kernels for AMD Instinct MI355X. On real model activations, its FP8 kernels run 1.16-1.76x faster than AMD’s AITER, with 62-78% lower error at head dimension 128. The post Zyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1.76x Faster appeared first on MarkTechPost.

Information-Matched Auditing of Conversational Emotion-Shift Forecasting: A Leakage-Safe Evaluation Protocol

arXiv:2611.05895v1 Announce Type: new Abstract: Comparisons in conversational emotion-shift forecasting are easily distorted when a learned model receives rich features but its transition baseline is given a noisy or unavailable current-emotion label, when hyperparameter budgets differ, or when target-turn information enters the representation. We present an information-matched, leakage-safe auditing protocol that closes these gaps with an explicit commitment point, executable causality tests, equal four-configuration validation searches, and seed-dialogue-aware inference. Applying it to six causal model families on four text corpora and two feature-source sensitivity configurations shows that a deployable train-only current-emotion classifier feeding the transition baseline yields a different verdict than an oracle diagnostic where both sides receive gold current emotion. Under the deployable condition, learned models improve over the predicted-label baseline on all four primary corpora; DailyDialog gains are large and survive a 72-comparison Holm correction (best ROC-AUC gain = +0.167, adjusted p=.0144). Under matched gold information, the baseline remains competitive on IEMOCAP and stronger on MELD, while every model retains a large DailyDialog advantage. We additionally report precision-recall AUC, calibration, a strictly utterance-local feature control, same-person self-shift forecasting, and a future-access dose-response test. An eight-item leakage checklist accompanies the protocol. Code, raw seed predictions, and reporting artifacts are available from the corresponding author upon request.

Measuring how AI agents handle everyday wet-lab science

OpenAI introduces BioBasicsBench, a 100-task benchmark measuring how well AI agents interpret raw experimental data and handle everyday wet-lab science.

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.

Does the Trust Boundary Hold over Time? A Long-Horizon Benchmark for Receiver-Directed Federated Learning

arXiv:2611.03724v1 Announce Type: new Abstract: In receiver-directed federated learning, each site draws a trust boundary. For every source and model component it judges, on its own data, whether the transfer helps (admit), harms (reject) or cannot yet be told (abstain). We ask whether this boundary holds over hundreds of rounds. Our benchmark has a federation of thirteen semi-synthetic sites, an exact oracle for every evaluated transfer, paired seeds, an attack protocol, fourteen methods over 600 rounds and Qwen3-1.7B LoRA sites over 500. The answer depends on which boundary is measured. Across 20 paired CPU seeds, a gate judging against a fixed reference better identified transfers useful relative to the site's starting model. Yet it admitted 29% of transfers harmful to the model the site now has. A gate judging against the current model admitted 2% of harmful transfers on that target in the CPU tier, but missed many transfers useful to the starting model. Two short propositions explain these distinct failures. We also evaluate a held out audit that leaves gate verdicts intact. After training, it decides whether each final model is deployed or the site falls back to local training, and reports admissions that have gone stale. With independent audit data its guarantees hold after any training history. At 600 rounds the audit deployed 65 to 72% of models, none with negative benefit on its target, and kept 98% of the gain. No stale report had the wrong sign in our runs. With 20,000 audit observations, a variance-adaptive bound found 99% of stale transfers that cost at least 0.01 in log loss. A common-target Qwen3 comparison on 60 selected transfers shows the same tension over 100 rounds. With 38% adversarial sites, FedFomo and CS-Gate were the only evaluated methods with positive mean gain in every honest group.

ScienceVision: Can AI Observe and Reason Like a Scientist?

arXiv:2611.04087v1 Announce Type: new Abstract: Scientific discovery builds on accurate observations interpreted through domain knowledge and reasoning. For scientific 3D data, this requires understanding structures and spatial relationships, from protein contacts to anatomical organization. Existing multimodal benchmarks largely evaluate text and 2D images, while scientific 3D evaluations vary in representations and protocols across disciplines, limiting cross-disciplinary comparison. To assess these foundational capabilities, we introduce ScienceVision, a cross-domain benchmark for scientific 3D understanding and reasoning through expert-level visual question answering (VQA). We construct 250 questions, with 50 each from Biology, Chemistry, Medical Imaging, Mechanical CAD, and Architecture, through a pipeline combining synthetic question generation with domain-expert review and annotation. Each task pairs a native 3D artifact with a scientific question, a specified response format, and a task-specific reference answer, requiring domain knowledge to be applied to geometric or topological evidence. We evaluate 12 models on the same questions in three settings: visual question answering with native 3D artifacts accessed through an agent harness's file and code-execution tools; the same workflow augmented with expert-inspired viewer inspection and measurement tools exposed through the Model Context Protocol (MCP); and visual question answering from prescribed rendered 2D images using an agent harness. All settings use the same task-specific deterministic final-answer scoring. The inspection environment supports view changes, target isolation, and slice inspection. In this main comparison, the best mean answer score is 0.53 out of 1. Mean scores in the native-artifact workflow without additional MCP tools exceed those in the rendered-image workflow for every model, by 17.2 percentage points on average.

Exposure Is Not Commitment: Double-Stratified Evaluation of Latent Monitors for Tool-Using Agents

arXiv:2610.37679v1 Announce Type: new Abstract: Tool-using language agents are vulnerable to indirect prompt injection, and a growing literature probes model internals to catch unsafe actions before they execute, with sharply conflicting results. We argue much of the conflict is an evaluation artifact, and propose a double-stratification protocol: separate injection exposure from behavioral commitment, in both the evaluation and the training population. On the primary Qwen AgentDojo grid, monitors trained on the naive mixed unsafe-versus-rest contrast mostly learn exposure: they flag exposed trajectories whether or not the agent complies, and barely predict which cases turn unsafe. Retrained on exposed cases only, the same probe families predict the model's own unsafe tool call up to two s

Scoring Explanations Without Reading Them: Structural Shortcuts in Automated-Interpretability Evaluation Data

arXiv:2610.37676v1 Announce Type: new Abstract: Automated interpretability scores an explanation of a sparse-autoencoder (SAE) feature by asking a model to predict, token by token, where the feature fires on evaluation examples or to judge whether marked tokens fit it. We find that the evaluation data standard pipelines build can be scored without reading the explanation. On Neuronpedia's stored fuzzing runs for 500 random GPT-2 small features, 91.3% of activating examples are cropped with the peak on the centre token, and a rule that says "yes" when the centre token is marked reaches balanced accuracy 0.979, against 0.838 for the stored LLM scorers (recomputed from the stored per-item verdicts, on marks rebuilt from the pipeline's code); a rule reading only the mark count reaches 0.969. T

Nvidia releases all-in-one adaptable Nemotron 3.5 audio transcription and translation model

Nvidia Corp. today released a leaderboard-winning open artificial intelligence model for multilingual audio transcription and translation, along with an open data pipeline for fine-tuning Nemotron 3.5 Transcribe. Traditional transcription AI models follow a workflow that detects speech, transcribes it, identifies and labels different speakers, then answers questions about the transcription. Transcribe does all of this […] The post Nvidia releases all-in-one adaptable Nemotron 3.5 audio transcription and translation model appeared first on SiliconANGLE.

Fix evaluation bias to unlock better models on Amazon Bedrock

Property Finder found that 96.8% of their vision-AI evaluation labels were inherited from the incumbent model, hiding its true accuracy. See how they built unbiased ground truth, applied evolutionary prompt optimization, and selected a more accurate, cost-effective model on Amazon Bedrock, cutting cost by 86% across 11 image-quality attributes.

Exowatt beats frontier models on accuracy with SageMaker serverless model customization

In this post, we show how Exowatt used Amazon SageMaker AI serverless model customization to build a repeatable AI pipeline that produces task-specific fine-tuned models for two deployment targets, edge and cloud, achieving higher accuracy than frontier models at up to 49x lower cost.

Baidu Open-Sources Unlimited OCR 2 for Hundred-Page Document Parsing

Baidu has released Unlimited OCR 2, an MIT-licensed 3B OCR model that parses hundred-page documents in one request. Its SR-SWA attention keeps per-step decoding cost nearly flat, scoring 77.1 on MarathonDocBench The post Baidu Open-Sources Unlimited OCR 2 for Hundred-Page Document Parsing appeared first on MarkTechPost.

AdaptTok-Indic: Script-Aware Adaptive Tokenization for Indic Languages

arXiv:2610.33017v1 Announce Type: new Abstract: Multilingual tokenizers trained on English-dominated corpora often over-segment Indic languages, resulting in longer token sequences and increased tokenization disparity across scripts. We present AdaptTok-Indic, an Indic-specialized extension of adaptive tokenization that combines Unicode-normalized preprocessing with explicit Indic conjunct handling, script-aware routing, and learned byte-level boundary prediction jointly trained with a small Transformer language model. Evaluated on Bengali and Hindi, with additional evaluation on Gujarati, Tamil, and Telugu, AdaptTok-Indic achieves lower token fertility than SentencePiece BPE, an Indic-oriented tokenizer baseline, and an independently implemented MAGNET-style baseline. Across five recorded

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

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.

Tampered ML: Evaluating LLM Judgment of Machine Learning Research

arXiv:2610.32114v1 Announce Type: new Abstract: One approach to accelerating progress on AI alignment is to automate parts of alignment research itself. Doing so requires systems that can perform reliably on hard-to-supervise research tasks, including identifying flaws in research proposals and evaluating whether a proposed experiment supports its intended claim. To evaluate this capability, we introduce Tampered ML, a benchmark of 1,858 item-pairs, each consisting of an experiment proposal reconstructed from a published machine learning paper and a minimally edited counterfactual that introduces a targeted methodological flaw. Models must identify the more methodologically sound proposal in both presentation orders. A human validation study on a stratified sample estimates that 86% of ite

SAGE Benchmark and GAR Framework Released: Advancing Multimodal Semantic Alignment Evaluation

On October 26, 2026, arXiv published the paper arXiv:2610.31838v1, introducing Sense-Aligned Grounding Evaluation (SAGE)—a unified 10-candidate image-selection benchmark—along with the training‑agnostic Gloss-Augmented Reasoning (GAR) framework, designed for cross‑noun, verb, and entity‑centered multimodal grounding evaluation.

Why it matters：This study is the first to unify three types of tasks—VWSD, VerSe, and WikiDiverse—under a term-centric grounded evaluation protocol, introducing a mechanism for identifying hard negative samples and context‑exchange diagnostics. Empirical results demonstrate that the synergistic effect of definition enhancement and constraint‑guided reasoning can significantly improve the Hits@1 metric (from 65.90 to 71.22), thereby providing a more fine-grained, interpretable new evaluation paradigm for multimodal semantic alignment.