Set up Amazon Bedrock AgentCore Observability for AI agents running outside AWS: on-premises, on GCP, on Azure, or on developer machines. This walkthrough uses the AWS Distro for OpenTelemetry (ADOT) and IAM credentials to route session traces, span metrics, and token usage to the same AgentCore Observability dashboard.
Claude apps gateway is a self-hosted governance layer between Claude Code and Claude Desktop and Amazon Bedrock or Claude Platform on AWS. This post presents a production reference deployment covering end-to-end architecture, enterprise deployment patterns, cost, and implementation resources.
Decision models choose among predefined options in tasks such as routing and action selection. In multi-agent collaboration, a decision determines how members divide work, exchange resources, and act in parallel. We introduce TandemBench, a benchmark of 1,200 questions in multi-agent cooking scenarios where coordination choices affect goal completion. Models receive complete global information and candidate team plans, with reference answers established through execution and exact search. Models select an optimal team plan and, in paired variants that retain or remove it, judge whether better arrangements exist beyond the supplied options. We evaluate 40 native decision models and compare them with 10 general-purpose language models. The best native decision model achieves 62.50% decision accuracy. Native decision models remain close to chance in optimality verification. Paired tests reveal that some report better alternatives regardless of whether an optimal plan is already present. These findings show that team-plan decision accuracy alone can conceal systematic errors in judging whether the supplied options contain an optimal arrangement. The dataset and evaluation code are publicly available at https://github.com/lililibaohang/TandemBench.
Gen Digital built Norton Revamp, a generative AI-powered professional reputation management platform, with an AI-curated News Engine grounded by Web Search on Amazon Bedrock AgentCore. See how the Gen team delivers real-time, cited content suggestions, goal setting, and news feeds with zero data egress and Norton-grade privacy.
Large language model (LLM) services face rapidly rising serving costs. To sustain free or affordable access for a broad user base, alternative monetization mechanisms are needed. Native advertising offers a promising approach, as it creates economic value by aligning user intent with merchant offerings. Yet how to integrate sponsored content naturally into LLM responses remains largely underexplored. Existing approaches primarily rely on prompt-level injection, multi-pass rewriting, or fine-tuning, which can compromise response quality or introduce additional computational costs. We propose AdSteer, a lightweight decoding-time advertising framework that adaptively adjusts token probabilities to integrate contextually appropriate advertisement into responses. AdSteer calibrates the strength and duration of advertising influence, making sponsored content a natural part of the response. Experiments on GEM-Bench across three application scenarios show that AdSteer achieves an average improvement of 14.1% in overall score over the strongest baselines and 22.5% fewer total tokens on average than rewrite-based methods. These results demonstrate that AdSteer provides an effective and practical solution for native advertising in LLMs.
Learn how to build a multi-agent engineering assistant that compresses aerospace component substitution evaluation from days to minutes, using Amazon Nova Multimodal Embeddings, Amazon Bedrock AgentCore, and the Strands Agents SDK to assemble substitution evidence while keeping the engineer as the decision-maker.
Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-extracted text. We instead ask whether vision-language models (VLMs) can enable page-native deep research: directly retrieving and reasoning over rendered document page images. We introduce DR Pixel, the first open-source end-to-end multimodal DR agent that uses rendered page images as its sole retrieval and reasoning unit, operating over a corpus of 1.06M pages. To evaluate this setting, we construct DRPixelBench, a benchmark on scientific papers requiring reasoning over text, figures, tables, and equations. Surprisingly, page-native DR already works well without training, outperforming OCR-based baselines across state-of-the-art models like GPT-5.4, Gemini-3.5-Flash, and Qwen3.6-27B, while requiring fewer tool calls. We next turn to DR training. A key challenge is that teacher trajectories for agentic supervised finetuning are noisy, mixing critical reasoning and action steps with redundant or failed attempts. To address this, we introduce counterfactual credit reweighting, a fine-grained credit assignment method that weights individual reasoning and action steps by their counterfactual contribution to the final answer. Our training improves retrieval recall by about 15 points and final accuracy by over 10 points on DRPixelBench, and likewise outperforms the untrained baseline on four existing benchmarks. On out-of-distribution ViDoRe-V3, DR Pixel comes within 1.8 points of an oracle that is given the gold pages directly. Our results suggest that the conventional OCR-then-retrieve pipeline is not only unnecessary but suboptimal: directly retrieving and reasoning over visual document pages makes complex DR both more effective and more efficient.
Google Workspace now offers native support for Markdown (.md) files, allowing developers and AI agents to seamlessly collaborate on documentation directly in Google Docs without manual file conversions. This integration preserves native file fidelity for use with Git repositories and developer tools while unlocking standard Docs features like line-level commenting, rendered Drive previews, and tracked version history.
A hulking gray giant rises from the desert. Inside, engineers create the force behind our phones and computers and appliances, our streaming services and search…
Frontier language models express coherent preferences, but behavioral evidence alone cannot say whether these belong to the model or to a character it portrays. Following Hofstadter's view of the self as a self-description, we ask whether a model's description of itself works as a portable specification of its preference profile, a quine test: can the text a model writes about itself regenerate its behavior elsewhere? Ten models from nine labs write self-descriptions; we place each one in the prompt of other models (receivers) and of fresh instances of the author, and measure how closely their choices on a 110-item preference battery match the author's. First, the tested native self-descriptions (native: the profile measured under a generic assistant prompt) show no average reconstruction gain across variations in length, framing, wording and prompt placement: on a 0 to 1 fidelity scale where a model's fidelity to a fresh instance of itself is 0.979 and to unrelated models about 0.89, the one-sided 95% upper bound on the pooled gain is below +0.01 in every tested system-prompt condition, and descriptions based on the author's observed choices do no better. Second, the channel itself is strong: explicitly listing the author's answers lets receivers reproduce its profile at fidelity 0.955 to 0.960 across three model grids, within 0.03 of same-model repeatability. Third, self-descriptions written under an explicit preference policy transfer the assigned preferences almost as well as the policy text itself. Fourth, reading its own self-description shifts even the author away from its baseline, modestly more than unrelated prose of the same length. For the preferences measured here, native self-descriptions influence behavior without reliably specifying how to reproduce it in another model. We release the pipeline, battery, raw call logs, and 198 model-written descriptions.
Vision-language models used for decisions in histopathology rarely return calibrated probabilities over the candidates a user cares about. Decision-native models write a question and a candidate set chosen at run time into the input and return a normalised distribution from a small decision head in one forward pass. We build PathJev-P, a decision-native model for histopathology: MedGemma-1.5-4B with LoRA adapters and a decision head, trained on 40,000 patch states from three public collections whose expert labels are turned into typed questions with organ-specific candidate sets and a "none of these" option. In a comparison over 3 seeds with an analysis plan fixed before testing, on test sets without documented overlap with the training data of the backbone, PathJev-P is more accurate than a generative model trained with the same backbone, data and selection rule, the zero-shot pathology model CONCH and a general medical decision model (balanced accuracy 0.541 against 0.492, 0.345 and 0.213); its advantage over the generative model comes from two organs absent from training. The calibration advantage depends on how the generative model's probabilities are read out. With the summed candidate log-likelihood used in previous work, PathJev-P has the lower calibration error (ECE 0.204 against 0.279); with a length-normalised read-out of the same generative model, examined post hoc, the two have similar mean calibration error (0.201) and the generative model is better calibrated on the unseen organs, where PathJev-P remains over-confident. A supervised linear probe on a pathology foundation model is better calibrated in every setting. In a qualitative whole-slide demonstration, PathJev-P labels unsupervised tissue clusters with abstention and separates carcinoma from other tissue while running the model on a fraction of the tiles.
Deepgram worked with the AWS Forward Deployed Engineering team to port its Nova-3 speech-to-text model to AWS Trainium2 for offline batch inference. This post covers porting to the AWS Neuron stack, kernel-level tuning, a data-parallel Rust runtime, and the throughput and cost results on batch transcription.
Reflection AI's Beam is an open-weight model for agentic coding and long-horizon tasks. This post shows how to deploy Beam on AWS: start with an Amazon SageMaker JumpStart real-time endpoint, or use Amazon SageMaker HyperPod Inference with JumpStart, SGLang, or vLLM for Kubernetes-native control over distributed GPU infrastructure.
A monthly recap of the latest Amazon Bedrock, Amazon Bedrock AgentCore, and Strands updates from September 2026: broader model choice, faster serverless agents with built-in evaluation, and automated knowledge base syncing with native enterprise connectors.
Building an AI agent that works in a demo is a different problem from running one for 40 million developers. Postman and AWS share the architectural patterns behind Agent Mode: controlling tool sprawl, exposing schema-based reads, and treating context as the real bottleneck, plus how it runs on Amazon Bedrock at scale.
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research .
We construct neural approximation classes native to the graph spaces H(div) and H(curl), in two and three dimensions and, for H(div), in any dimension. Every realization lies in the space for all parameter values, and with kinked potentials, such as ReLU networks, the admissible jumps appear at finite width. The classes are images of scalar and componentwise networks under fixed operators of the de Rham complex, and do not involve a mesh or finite element emulation. For H(div) in R^n two native classes are given on an equal footing, with a skew-symmetric potential A: Div\,A+R_nq+h, with the divergence q as an explicit unknown, and Div\,A+z with an H^1 field z; for H(curl) the analogous classes are grad\,φ+Sr+h in two dimensions and grad\,φ+z in two and three dimensions. In all of them every interface jump of the field is carried by the potential term, Div\,A or grad\,φ, while the remaining part has no interface jump (it is an H^1 field in the regular-decomposition classes); the classes with z are the componentwise approach enriched by this term. Known or learned interface geometry enters the potential through factors with trainable amplitudes, and the remaining part if the divergence jumps. The classes lead to the FOSLS-deRhaNN method, first-order system least squares with de Rham neural networks, whose loss is the least-squares functional posed in the natural spaces of the weak formulation; for elliptic equations this includes H^{-1} right-hand sides and H^{1/2} Dirichlet data. Elliptic equations with discontinuous coefficients and curl-curl problems are treated as instances, with the functional equivalent to the error; linear transport with discontinuous solutions and conservation laws with shocks use the same flux classes.
Manually extracting data from hundreds of vendor contracts doesn't scale, and RAG chat tools fall short on portfolio-wide questions. This post shares a contract intelligence platform on AWS that uses AI agents to extract and verify contract fields, then answers aggregate and single-contract questions through Amazon Quick analytics.
A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. We study how local serving stacks affect this protocol step and show that measured outcomes can depend on the serving layer rather than model behavior alone. In Ollama, the default tools= request is gated per model by a static template flag: some models are accepted and return calls as text, some return native tool_calls, while Phi-3 and Gemma-3 are rejected before inference. In our harness, rejection and retry exhaustion are not preserved as structured failure metadata, so downstream analysis can misclassify them as model non-calls and naively report 0% fidelity. Adding a text tool list while retaining the native channel recovers much of the measured fidelity for accepted models, whereas a uniform text protocol reduces fidelity for Llama-3.2, which has native tool-call support. Cross-stack probes on Ollama, llama.cpp, vLLM, and SGLang show different handling of the same request. Constrained decoding removes parse failures but can induce non-termination, and turn-pooled versus per-instance estimates differ by up to about 55 points. We conclude with a checklist for treating serving behavior as part of the evaluation protocol.
