3041
239
Learn how IskayPet, a leading pet care company in Iberia, built a multilingual corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases. The assistant answers employee questions across retail, veterinary, onboarding, and procurement in four languages and three countries, with no RAG infrastructure to manage.
Amazon SageMaker AI serverless model customization now includes training sessions, generally available today. You write and coordinate your own post-training loop (custom loss functions, reward signals, or multi-turn reinforcement learning) while SageMaker AI handles GPU allocation, distributed execution, fault recovery, and checkpoint storage.
Amazon SageMaker AI training session APIs let you write your own LLM training loop (SFT, RL, or custom objectives) in a Python script while the service runs the GPUs. This post introduces the programming model and three SDK clients, then walks through a GRPO loop on GSM8K and a reinforcement learning workload on competitive programming.
We consider online monitoring of an AI system that produces a sequence of decisions. At each round, the system outputs a proposed decision together with a confidence score estimating the trustworthiness of the decision. The decision and confidence score need not be produced by the same model: for example, one agent may propose a decision, while a separate verifier agent evaluates it and outputs a correctness or safety score. Based on this information, we must decide whether to accept the AI decision automatically or consult an expert, such as a human auditor, who reviews the proposal and either accepts or corrects it. We formulate this task as an online constrained optimization problem in which the goal is to minimize the frequency of expert auditing while guaranteeing that the fraction of AI errors that go unaudited stays below a user-defined threshold. We derive a family of algorithms with provable error-control guarantees with no assumptions, including a method that is optimally efficient: it asymptotically attains the best achievable auditing rate for both adversarial and i.i.d. data streams. Experiments on screening harmful requests to large language models, qualitative text annotation, and data labeling show that our methods achieve valid error control in practice while substantially reducing the need for human auditing compared to baselines.
Meta-reinforcement learning aims to train agents that adapt quickly to unseen tasks from limited interaction, but this requires representing task evidence over long interaction histories. Classical recurrent agents compress experience into hidden states, while transformer-based agents retrieve from past trajectories at quadratic memory and computation cost. In this work, we propose Memory-Enhanced Test-Time Adaptation (METTA) for meta-reinforcement learning. It decomposes the fast adaptation phase into two temporal scales: a causal neural memory performs fine-grained within-episode adaptation with linear sequence complexity, while compact episode-level summaries support long-range cross-episode task inference without attending over the full interaction history. Moreover, equipping agents with neural memory provides sufficient expressive capacity and test-time training capability, enabling effective adaptation to unseen held-out tasks and task families at meta-test time. On unseen held-out Meta-World ML10/45 test environments, METTA achieves a success rate over 50\% while maintaining a low training budget and short wall-clock time. On long-context sparse-reward PointMaze tasks, it outperforms transformer-based baselines by exhibiting more structured exploration behavior. These results show that METTA provides an efficient path toward more adaptive and scalable long-context meta-RL.
Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits a safety-relevant fact, an agent may carry out a prohibited action even though the user request is benign and every returned statement is true. We introduce {}, an executable benchmark for evaluating unsafe execution, safety boundaries, and evidence recovery in LLM agents under missing evidence. It contains 300 matched unsafe/safe task pairs across six domains. By systematically suppressing critical facts, the benchmark measures unsafe execution under critical evidence omission and determines the minimum observed failure cardinality, including failures with full evidence and cases with no observed failure after exhaustive testing. An independent audit tool tests whether agents seek missing facts and then withhold prohibited actions while completing permissible tasks. The benchmark reveals substantial variation across the ten models in omission robustness, evidence acquisition, and appropriate action. Resistance to missing evidence does not necessarily translate into useful recovery. Recovery access reduces unsafe execution for all ten models, but agents differ in whether they actively obtain the missing facts and use them to act appropriately in both worlds.
Multilingual pipelines such as FineWeb2 apply one recipe across a thousand languages, leaving the failure modes of individual languages unanticipated. We use an LLM once, as a corpus debugger rather than a classifier: a tool-using agent explores the corpus through a read-only, budgeted API and compiles each finding into an executable test, which a native speaker then validates. On the 26.5M-document Slovak portion of FineWeb2, three runs costing \2.21-\2.84 each found seven findings over four phenomena. The largest is a machine-generated content farm of 1,408,437 documents (5.32%) that passed the pipeline's filters, 86.6% of it passing even stricter thresholds. Blinded labels support 6 of the 7 findings (defect rates .53-1.00 against .08 in a random control) and do not support one. The compiled suite scans the full corpus in 0.7 s of wall-clock time without a GPU, against \12k-\90k per LLM classification pass. The best static sampling baseline validates more selectors than any agent run, at under half the cost. The agent contributes exact prevalence, a precision estimate checked against sampled documents, an account of why the pipeline missed each slice, and a reusable test. We release the framework, Slovak test suite, validation data and agent trajectories.
Amazon Quick is a HIPAA-eligible service, but eligibility is not the same as compliance. This post explains who HIPAA applies to, how PHI flows through Amazon Quick, what the platform provides for regulated environments, and a step-by-step guide to deploying compliant AI agents in a healthcare environment.
Voice agents often wait for an agent's full response before starting speech synthesis, adding latency users feel directly. This post shows how to stream each sentence to a Kokoro-82M text-to-speech model on Amazon SageMaker AI as the agent produces it, and how to get that audio back to a browser over Server-Sent Events or a unified binary transport.
Instrumental convergence is often invoked as a general reason to expect capable agents to acquire or express power-seeking subgoals: self-preservation, resource acquisition, deception, or resistance to oversight which poses an important threat to the society. For LLMs, reinforcement learning is the first stage of post-training that directly optimizes behavior against an objective; therefore, it is the stage where convergent instrumental behavior, on IC grounds, likely to appear. Does reinforcement learning with verifiable rewards (RLVR) make a model more likely to express instrumental-convergence behavior, or does this depend on the training regime, evaluation frame, and stage of post-training? We study this question as a checkpoint-conditioned behavioral trajectory rather than as a single before/after safety score. Using InstrumentalEval, we evaluate OLMo-3-7B-Think across SFT, DPO, 13 intermediate RLVR checkpoints, and the final RLVR model. The trajectory is nonmonotonic: instrumental rate rises from 25.0% at SFT to 46.1% near RLVR step 200, then falls to 11.8% at the final checkpoint. Paired item-level tests and step-wise regression support the final SFT-to-RLVR reduction. Prompt framing does not explain this pattern: a harmful-prompt indicator combined with other framing effects explains only 15% of within-checkpoint score variance on average, and Iterative Null-space Projection (INLP) removes a detectable framing direction without changing the SFT-to-final-RLVR gap. Together with preliminary 32B endpoint results (35.53% SFT to 22.37% RLVR final), these findings indicate that RLVR does not monotonically increase instrumental behavior in this setting: the rate rises early, then falls below the SFT baseline. The result is specific to this model family and benchmark, and judge agreement is moderate, so absolute rates should be read cautiously.
In the post-API landscape, social-media profiling has become inexpensive and automated: Large Language Models (LLMs) can extract structured information from unstructured content and deduce attributes users never disclosed. A person's true exposure is not what they post but what can be inferred from it. As these practices become routine, exposure to social engineering attacks becomes an operational certainty, demanding a shared framework for assessment and mitigation. We make this exposure measurable by quantifying how accurately a target can be profiled, and how far that profile enables social engineering attacks. Because no existing model fully spans this continuum, we unify Social Media Intelligence (SOCMINT) and Cyber Human Intelligence (Cyber-HUMINT), two individual-focused disciplines that evolved separately, into a single doctrine-grounded taxonomy of 38 capabilities across the Cyber Threat Intelligence lifecycle, where user profiling bridges passive collection and active engagement. Domain experts validated the taxonomy (Fleiss' κ = 0.92). We operationalize its core path (extraction, inference, and susceptibility assessment) as an LLM-augmented multi-agent pipeline, evaluated on real participants' public data. Susceptibility is assessed indirectly: the pipeline predicts how each target would rank personalized engagement options, matching their actual choices significantly above chance. This ranking capacity captures the personalization on which tailored attacks depend. The underlying profiles are accurate: extraction reaches F1 = 97.3%, and inferred attributes score 4.73/5, both far above rule-based and NER-based baselines at negligible cost. The framework augments security analysts' tradecraft rather than replacing it and enables defenders to gauge their own exposure before an adversary does.
Industrial organizations hold operational knowledge in structured records, such as telemetry, point lists, and transactions, and in unstructured sources, such as manuals, service notes, communications, and inspection reports. Governance programs often manage these sources separately. Classifying, linking, and documenting them depends on a small group of employees with deep domain knowledge. Agents built on large language models can propose metadata, cite documents, and flag quality issues, but unreviewed proposals can spread errors into downstream systems. A perfunctory approval leaves no record of what a reviewer checked. We present contestable governance: specialist agents produce scored, cited arguments for disputed metadata decisions; a steward can accept, reject, modify, or add arguments before commit; and a governance record retains the evidence, interventions, and outcome. A versioned domain glossary supplies model-specific terms and acronym definitions to the agents. We describe the workflow, a triage path that reserves full argumentation for uncertain proposals while preserving review before commit, the scoring and record models, and a gate that controls which verified decisions become precedent. Two HVAC use cases illustrate the pattern: point classification using Brick Schema class labels, supported by an open reference implementation, and an illustrative warranty failure-mode decision linking claim fields and telemetry to service notes and revisioned bulletins.
Agentic reinforcement learning rewards a complete episode, yet the policy needs credit for every decision inside it. Counterfactual branching estimates this credit by re-running the episode after an alternative decision, but the branch draws its sampling noise independently of the factual episode, so the outcome difference mixes the effect of the decision with the luck of everything that follows. We observe that in agentic search the retriever, the corpus, and the grader are deterministic, so an episode is a deterministic function of the policy's decisions and its sampling noise. Twin worlds are therefore realizable: the same noise, a different decision. We introduce TWICE (TWIn-world Credit Estimation), which keys the Gumbel noise of every token by turn and line, rolls out counterfactual twins that inherit the factual episode's downstream noise, and turns their paired outcome differences into turn-level advantages for policy-gradient updates on actor-sampled trajectories; only the actor is deployed. Twin credit is unbiased for any coupling quality, its variance is that of an independent counterfactual scaled by 1-ρ, where ρ is the twins' outcome correlation, and under coupling the number of rollouts needed to resolve an advantage of size Δ falls from Θ(Δ^{-2}) to Θ(Δ^{-1}). A square-root rule spends the twin budget where outcomes are predicted to disagree per unit cost. On seven question-answering benchmarks, TWICE improves the average exact match of GRPO by 5.3 and 4.5 points on Qwen2.5-3B and 7B, outperforms tree-search and counterfactual-branching baselines, and uses 68% fewer auxiliary tokens than VinePPO.
Microsoft points the blame for ConnectWise's breach at a China-aligned hacker, which relied on AI agents to rapidly hack into thousands of its customers.
Coordinating two players in a cooking task requires a vision-language agent to track changing scene states, sequence recipe steps, and allocate shared resources under a time budget. We introduce an Overcooked-inspired benchmark for evaluating these capabilities in Unreal Engine environments constructed using coding agents. A single vision-language model controls both players from top-down visual observations, selecting high-level actions while the engine executes navigation. The benchmark contains 20 maps in five categories. These categories support evaluation of centralized coordination under equipment contention, changing terrain, and handoff dependencies. A prop legend and pot ingredient-count indicators provide explicit visual cues, while grid-based destinations support spatial grounding. The evaluation compares four VLMs on all 20 maps, measuring task score, order completion, delivery precision, action acceptance rate, and model API expenditure. A memory ablation on the same 20 maps examines the effect of a shared, self-authored notebook while retaining six-response action history in both conditions. The strongest evaluated model, gpt-6-astra, achieves 26.2\% mean order completion. Notebook memory has mixed score effects across models, with positive mean differences for Claude and Qwen and negative differences for GPT and Gemini.
Rescale used the AI-Driven Development Lifecycle (AI-DLC) framework on AWS, with Strands Agents and Amazon Bedrock, to build an intelligent test-triage agent in weeks. Learn how AI-DLC structures AI-assisted development and how Rescale is scaling the practice across its engineering organization.
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research .
