2441
179
In production AI agents, context management is the real bottleneck. This post presents a four-layer context engineering framework (architecture, prompts, file-based tools, and verification agents), implemented in working code from Deep Insight, an open source multi-agent data analysis solution on the Strands Agents SDK and Amazon Bedrock AgentCore.
This post explores how Indegene built a production-grade, LLM-powered Data Quality Agent in its NEXT Unified Data Platform on AWS. The agent generates context-aware data quality rules, validates them, and produces ready-to-run SQL and Python under human-in-the-loop governance, helping life sciences organizations scale enterprise data quality.
U Mobile, Malaysia's newest 5G network provider, built AiDaH, an agentic AI operations platform on Amazon Bedrock AgentCore that moves beyond AI assistance to autonomous action across telco operations. Nine months after production launch, AiDaH handles over 150 operational scenarios across six divisions, cutting trouble tickets by up to 84.5%.
Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. This long-term drift is often mitigated through training on multi-turn data or cross-turn rollouts, potentially altering pretrained priors, or through specialized inference-time mechanisms that are difficult to scale to foundation models. We introduce TailSteer, a final-stage training framework that improves multi-turn robustness while retaining the generative and editing capabilities acquired through earlier training. TailSteer follows a simple principle: keep early denoising dynamics close to those of the base model and concentrate preservation corrections near the trajectory tail, where fine-grained deviations can be suppressed. These corrections are learned from the editor's own on-policy denoising rollouts, using unchanged source content as a preservation reference without requiring curated ground-truth editing pairs. Experiments across the FLUX, SenseNova, and Qwen families show that TailSteer substantially reduces cumulative drift over 15-20 editing turns while largely preserving base-model performance on extensive text-to-image and single-image editing benchmarks. These results demonstrate that long-horizon editing robustness can be unlocked in foundation models after TailSteer, rather than by relearning their existing capabilities.
Streaming video understanding requires models to repeatedly decide whether to respond or continue observing. Recently, Group Relative Policy Optimization (GRPO) has been applied to this setting, with existing approaches emphasizing reward design while retaining a single trajectory-level advantage across turns. Such shared credit can reinforce redundant replies after earlier successes and discourage useful follow-ups after earlier failures. We propose TurnWise, a turn-level GRPO framework that aligns learning with individual streaming decisions. TurnWise addresses the mismatch between trajectory-level feedback and turn-level interaction, promoting informative responses and reducing redundancy. Specifically, turn-level credit assignment uses silence-completed prefix scoring to construct group-relative advantages from each decision's remaining return, separating its learning signal from earlier rewards. Turn-mean policy optimization averages token losses within each turn and then across turns, giving response and waiting decisions equal weight regardless of output length. These complementary designs improve streaming policy learning without a learned critic or additional rollouts. Extensive experiments show our method outperforms prior RL approaches for streaming video understanding.
Dexterous robotic hands are increasingly coupled to large-scale human data and foundation models, yet progress in hardware, representation learning and evaluation is often assessed separately. This survey reviews work from January 2024 to early November 2026, with earlier studies included to establish technical lineages. We organize the literature into five interdependent layers: hardware; data collection and curation; cross-embodiment transfer; learning and foundation models; and evaluation and applications. Human hand-object understanding and tactile sensing provide two cross-cutting perspectives. A system-level architecture, comparative tables and five case analyses connect design choices across these layers. We distinguish within-study experimental comparisons from heterogeneous corpus statistics, vendor specifications and company-reported results. Three conclusions emerge. First, the value of human data depends on kinematic, visual and contact alignment, not recording volume alone. Second, shared action representations and foundation policies do not remove embodiment-specific constraints on force, latency and contact. Third, task completion is insufficient to establish physical correctness or deployment readiness. Evidence remains limited for zero-shot transfer of contact-rich skills between morphologically different hands, long-duration reliability, and cross-sensor tactile generalization. We identify eleven open problems and propose reporting interfaces and controlled comparisons that can make full-stack progress more measurable. The review is a structured narrative synthesis rather than a pooled performance ranking or an exhaustive systematic review.
Setting. This is an empirical characterization study; we propose no new method and run no comparisons against alternative objectives. We fine-tune Qwen3.5-4B with sparse LoRA and length-normalized DPO plus an SFT retention term (the RPO objective) on structured financial-filing tasks, and track downstream capability as the implicit reward margin grows to 7 β-scaled units (nf4 training; 3 under fp16 measurement on the unquantized base). Question. Does margin growth degrade capability uniformly across tasks, or selectively? Findings. In a pre-registered study (8 seeds, 6 unseen at freeze) with artifact-aware scoring and TOST equivalence testing, the alignment tax is graded and task-selective: extraction is preserved (Δ= -0.55 pts, equivalent at 5 pts), json loses little (Δ= -3.52 pts, equivalence fails on a clustered item-level interval), and router degrades severely (Δ= -30 pts). Router's loss concentrates in a margin 1-3 damage window containing a transient format-break spike. The margin is accounted for almost entirely (96\%) by suppression of rejected completions, with chosen reward approximately flat, consistent with the retention term anchoring it; we do not attribute the behavioral damage to any single gradient channel. Gold-logp deflation is task-selective (extraction -0.15, json -1.04, router -1.47 nats/token under fp16), with gold selectively protected relative to incorrect controls on extraction (8/8 seeds). QLoRA reward margins differ up to 3.4between nf4 training and unquantized fp16 measurement, with an axis-dependent gap. Scope. Length-normalized rewards with SFT retention, sparse LoRA on 8/32 layers, one 4B model, easily-separable synthetic preferences, three structured tasks. A no-retention control and a measured format-alignment metric are left to future work.
Traditional document parsing systems use Markdown as their output representation, which is effective for linear text but does not fully preserve fine-grained spatial structure, table geometry, visual hierarchy, or rendering semantics. We show that HTML is advantageous for heterogeneous and layout-sensitive documents whose representations must remain editable, inspectable, and reusable, and introduce AmbiHTMLBench to systematically study this setting. In this benchmark, given a real-world document, a model must recover executable HTML that preserves its content, organization, and visual appearance. The benchmark contains 1,115 diverse pages with structured annotations and evaluates predictions in two different ways: The objective protocol aligns ground-truth and predicted rendered blocks and measures table fidelity, page-level text error, and a two-dimensional layout consistency; a complementary reference-anchored protocol measures perceived fidelity by aligning LLM judges with human preferences. Across ten primary multimodal systems, the best objective score is 0.8092, while the subjective winner is different, demonstrating that automatic decomposition and human-perceived fidelity capture complementary properties. We further fine-tune a small-parameter expert model and find that task-specific adaptation yields good performance on document-to-HTML reconstruction task. These results position AmbiHTMLBench as a diagnostic testbed for building smarter and more logical document parsing systems.
Multivariate time series anomaly detection (MTSAD) relies on modeling both temporal dynamics and inter-sensor dependencies to identify complex system faults. Although graph-based detectors explicitly model sensor topologies, they train task-specific networks from scratch on limited target-domain data, remaining vulnerable to spurious correlations and unable to reuse transferable priors. While pretrained Graph Foundation Models (GFMs) offer transferable topological priors and anomaly discriminability, directly adapting them to MTSAD is hindered by cross-modal feature-topology mismatch, unreliable pseudo-anomaly supervision, and decision distortion during node-to-window aggregation. To fill these gaps, we propose a novel adaptation framework, Gfm4Mtsad, which unleashes pretrained GFMs for MTSAD. We introduce the Structure-and-Information Contract Alignment (SICA) module to bridge continuous time series and the pretrained GFM space. This module harmonizes principal subspace token projection, normal-prior-guided graph construction, and residual recovery to suppress spurious edges while retaining fine-grained temporal details. We propose a Mechanism-Aligned Pseudo-Anomaly Screening strategy (MAPS) to steer unsupervised learning. It applies localized dependency breaks while preserving empirical residuals, selecting hard negatives near the normal boundary for targeted supervision. We develop a Tail-Gated Evidence Calibration mechanism (TGEC) to eliminate node-to-window aggregation distortion. It calibrates multi-granular graph responses against normal operational references, strictly preserving benign score rankings while selectively refining extreme anomaly candidates in the tail distribution for reliable window detection and interpretable sensor evidence. Extensive evaluations with two GFM backbones demonstrate that Gfm4Mtsad achieves superior detection performance over existing baselines.
Achieving both high pronunciation accuracy and fine-grained controllability remains a central challenge in Japanese text-to-speech (TTS), as Japanese is an unsegmented language mixing logographic Kanji and phonographic Kana with extensive polyphony. Traditional cascaded systems convert text into phoneme sequences via a front-end, ensuring pronunciation control but discarding lexical semantics and prosodic cues in surface orthography. Conversely, recent zero-shot TTS models directly consume raw orthographic text to improve naturalness, yet suffer from polyphone errors and lack explicit pronunciation control. To bridge this gap, we propose a two-stage framework for flow-matching TTS. First, we investigate Ruby text representations with orthography perturbation to jointly preserve surface forms and target pronunciations for reliable control. Second, we introduce On-Policy Distillation (OPD) on large-scale text-only corpora to enhance pronunciation accuracy on raw orthographic text without paired speech. On the Joyo-Kanji-Yomi benchmark, our model achieves 97.13% Accuracy, 2.02% Target PER, 0.70% Sentence PER, and 4.21% Sentence CER under raw text while retaining strong controllability.
QA-based text embeddings represent texts as vectors consisting of 1/0 answers to yes/no questions. Although these embeddings provide detailed information for interpretation and achieve high task performance, they often require humans to examine a large number of questions. Furthermore, the relationship between the number of questions and the appropriate level of question granularity has not been sufficiently studied. To address these challenges, we propose a method for constructing hierarchical questions for text embeddings. As the hierarchy deepens, questions become more specific and their number increases. During interpretation, we reduce the number of questions that humans need to examine by replacing questions at deeper levels with aligned questions at shallower levels. The question hierarchy is constructed through recursive clustering, contrastive prompting, and question alignment. Experimental results on general-purpose tasks show that our method improves interpretability while maintaining task performance. It is also found that, when only a limited number of questions are available, questions at shallower levels tend to achieve higher task performance than those at deeper levels, even with the same number of questions.
Offline reinforcement learning with verifiable rewards (RLVR) trains on a fixed pool of sampled responses and typically supervises every token of every response, although responses and tokens are not equally informative. We study which ones to supervise through the Gibbs-optimal policy of KL-regularized RLVR, which offline training targets, and measure the mismatch between a policy and this target with a bidirectional KL divergence. At the reference policy, this mismatch factorizes exactly and separates the two outcomes: correct responses contribute mainly through the forward term, concentrated on their low-probability tokens, and incorrect responses through the reverse term, concentrated on the responses the policy generates often and on their high-probability tokens. Based on this analysis, we propose GIST (Gibbs-Targeted Hierarchical Data Selection), a two-level selection method that approximates these principles with signals available before training. GIST uses the sampling temperature to select correct responses on-policy and incorrect responses near the policy's mode, and it uses the initial policy's token probabilities to supervise only the tokens where the mismatch lies. Applied to two offline training objectives, GIST raises the average accuracy over GSM8K, MATH-500, and MBPP for all three models under both objectives. In a controlled comparison on Qwen3-0.6B/GSM8K, it outperforms seven selection baselines that choose from the same candidates while supervising 66.6% fewer tokens than training on all candidates of the same prompts.
Effective collaboration in multi-agent systems requires mechanisms for coordination and adaptability in dynamic and uncertain environments. However, existing multi-agent systems rarely model resilience explicitly, instead relying on ad-hoc output correction that limits systematic, runtime management of robustness. In this work, we propose Multi-Agent Mesh (MA-Mesh), a framework that constructs a role-based self-healing layer on top of a collaboration pattern. Specifically, MA-Mesh generates resilience-aware system specifications and synthesizes them into executable multi-agent policy code. To enhance resilience, we introduce two self-healing mechanisms: Cross-agent reflection, a mechanism that allows agents to evaluate not only their own outcomes but also the performance of their peers, enabling informed behavioral adjustments and collective policy refinement; Role-based failover, a strategy which dynamically reassigns roles and enables agents to substitute for one another when sub-tasks fail or agents underperform, ensuring continuity of task execution. Experimental results across diverse tasks (e.g., software development, tool use, scientific reasoning) demonstrate that MA-Mesh significantly outperforms existing multi-agent systems in both task performance and robustness under system uncertainty.
Typed decision models offer structured choices, scores, and probabilities for low-cost automated evaluation. We present a controlled audit of presentation sensitivity in Jev, Clef Flash, and Perplexity Decider across native choice and score interfaces. Across six datasets with 9,000 multiply annotated humor, helpfulness, and summarization items, we collect 702,000 judgments under interventions that vary positions, identifiers, authorship claims, endorsements, decision framing, and rating rubrics while preserving the evaluated texts. Jev's second-position probability advantage reaches 6.11 percentage points on summaries; reversing reader endorsements changes Perplexity's selected humor text on 40.40% of pairs; and rejection framing reduces Clef's summary agreement with human preferences by 23.36 points. Rating formats also shift score levels while often preserving rankings. Across these findings, repeatability, presentation robustness, and human alignment emerge as distinct properties of an evaluator. Reliable use therefore requires validating the decisions and score interpretations on which an evaluation pipeline depends.
Context compression reduces inference cost by encoding inputs into compact representations while preserving semantic content. An open question is whether semantic preservation alone is sufficient to maintain downstream behaviours such as refusal alignment. We investigate this question and find that encoder-based compression systematically weakens refusal behaviour in instruction-tuned language models, despite high reconstruction fidelity. This effect persists across model families and compression architectures. Mechanistic analysis shows that compression attenuates activation along the decoder's learned refusal direction. We further explore Memory Steering, a lightweight inference-time intervention that restores refusal rates to near-baseline levels without retraining and operates entirely in compressed representation space. These results demonstrate that semantic preservation does not guarantee behavioural preservation under compression, highlighting the need to explicitly preserve alignment-relevant features in compression-aware systems.
When many inputs share a budget of repeated attempts by a large language model (LLM), a common rule gives harder inputs more. On public math, code and formal-proof samples, the best published difficulty-proportional rule captures half or more of the oracle gain on benchmarks the model mostly solves, but at most 13% on hard workloads, even given true pass rates. Because the value of one more attempt peaks at intermediate difficulty, the optimal static allocation is inverted-U and gives little to inputs that are hopeless at the current budget. In a strict survey of 221 LLM allocation papers, at least 13 give the hardest inputs the most attempts; their easier settings sit at budgets where this is near-optimal, so the cost appears on harder workloads. Acting on it requires knowing which inputs are solvable, so information, not the policy, drives the gain. With a verifier and a prior from a related model's past runs on the same inputs, Thompson Sampling raises the solved share on the hardest workload from 14% to 27%; without such a prior, no policy we tested beats round-robin. For the policies we tested, the gain vanishes between prior rank correlations of about 0.3 and 0.55, which cheap text-based priors barely reach on the weakest models, and it requires a verifier whose false acceptances are rare relative to the pass rate. On new Qwen2.5 samples the pattern holds, and tempering the prior avoids losses on easy workloads. We turn these results into a decision guide.
Existing traffic signal control methods typically rely on structured traffic states produced by dedicated perception pipelines. Emerging visual approaches often use idealized simulator images and convert them into intermediate representations before control, limiting their ability to directly exploit roadside visual observations. To bridge both the visual-domain and perception-to-decision gaps, we introduce SynTra-V and Traffic-VL. SynTra-V converts physics-based traffic simulations into photorealistic multi-view surveillance imagery across diverse road topologies and sensing conditions, and automatic semantic auditing checks that control-critical geometry, vehicle movements, and lane semantics match the simulator state. Traffic-VL is an eight-billion-parameter vision-language model that directly maps synchronized multi-view images and natural-language phase descriptions to signal decisions without intermediate structured states. Building on Traffic-R1's two-stage reinforced reasoning framework, Traffic-VL adapts its vision encoder via offline reinforcement learning on SynTra-V and freezes it during online visual stepwise trajectory policy optimization in closed-loop simulation. Experiments show that Traffic-VL matches structured-state Traffic-R1 while outperforming image-based controllers and general-purpose vision-language models, including Gemini 3 Pro. Evaluations on unseen topologies, degraded sensing conditions, real surveillance footage, and a three-week deployment across ten intersections further demonstrate robust visual generalization and effective constrained online control.
Ambient sensors offer a privacy-preserving solution for activity recognition in smart homes, yet they face a critical challenge in multi-resident environments known as Data Association, which aims to identify the resident triggering a specific anonymous sensor event. Existing approaches fundamentally fail to maintain global consistency by often yielding conflicting associations for silent residents. Additionally, these methods frequently suffer from severe trajectory fragmentation caused by the ontological mismatch of applying continuous physical motion models to discrete logical behaviors. To address these limitations, we propose a novel framework that reformulates data association as a sequential decision-making task within a Markov Decision Process (MDP). We solve the defined MDP via Behavior Cloning (BC) to avoid complex reward engineering by directly learning from expert demonstrations. We instantiate the policy using two complementary architectures, including a lightweight Transformer that treats association as a multi-label classification task over linearized event histories, and a fine-tuned Large Language Model (LLM) that reformulates the problem as conditional text generation to leverage pre-trained semantic knowledge. Extensive evaluations on three diverse datasets demonstrate that our approach significantly outperforms state-of-the-art baselines, particularly in resolving concurrent multi-resident events. Furthermore, the LLM-based policy shows preliminary cross-environment transfer potential under benchmark settings, while its robustness in real deployments still requires further validation.
Pedestrians increasingly encounter robots in urban public spaces without interacting with them, but how robots change the perceived safety of a street remains unclear. We examine how robot presence and type affect perceived safety across urban contexts. We generate 18 images of Seoul streets that vary in time of day, road class, and robot condition (no robot, a delivery robot, or a humanoid). Two multimodal large language models (MLLMs), Qwen3.8-27B and Gemma4-26B, each conditioned on 500 synthetic personas, choose the safer image in each pair, and 25 human respondents complete the same task. Both models prefer streets without robots and favor the delivery robot over the humanoid. Robots are chosen more often at night and less often by older personas, whereas road class has smaller effects. In the model rationales, the delivery robot appears as a physical obstacle, whereas the humanoid appears as either a threat or a source of protection. Like humans, both models chose robots more often at night, but chose the humanoid over the delivery robot far less often, and Gemma showed a night effect for the humanoid about three times that of humans. These results show that the effect of a robot on perceived safety depends on when it appears, and that persona-conditioned MLLMs capture only part of human judgments.
RL for LLM reasoning often reaches an early performance plateau as the policy distribution becomes increasingly sharp. Recent work has studied policy entropy as both a diagnostic and a control signal for this behavior. In our experiments, however, increasing entropy alone does not reliably change the eventual plateau. We analyze RL through its implicit target policy and derive a sharpness factor κ, together with an effective counterpart κ_{eff}, that describes how strongly reward or advantage gaps are translated into probability-ratio gaps. Motivated by this view, we introduce reward budgeting, a plug-in advantage construction that assigns a fixed total reward budget to each prompt. For binary rewards and independent on-policy rollouts, its unclipped score-function estimator follows the gradient of an exact finite-G concave objective with diminishing returns, while its advantage gap decreases as more rollouts become correct. For general rewards, a shifted log-mean interpretation holds asymptotically under the stated regularity conditions. These results motivate, rather than establish exact objective equivalence for, the clipped implementations. On Qwen3-8B and Llama3.2-3B-Instruct, reward budgeting consistently improves a range of RL baselines, with gains up to +12.50 on AMC23 and +10.00 on AIME24 and AIME25. Overall, our results support an update-dynamics view of premature convergence and show that strong gains can be obtained without explicitly preserving entropy.
