Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems constructed from real-world legal, finance, medical, and software engineering corpora. TeamGym introduces a method to identify a minimal set of facts, each element of which is necessary and all of which are collectively sufficient for a correct final decision, which we call pivotal information. This enables TeamGym to both control the distribution of pivotal information and track how well agents identify and integrate pivotal information when making team decisions. Examining 8 language models on 12 source corpora, we find that current AI agents often fail to effectively share information: Distributing pivotal information across participants lowers success rate by 22.9 percentage points on average relative to giving the same information to a single model (a communication gap). We also document that participants do not effectively retrieve decision-relevant information on their own: A team's success rate is lowered by a further 19.9 points when participants must identify and extract pivotal information from source material rather than receiving it directly (a retrieval gap). To help remedy these deficits, we use TeamGym to train policies through reinforcement learning on team decision loss. Across two policy-training experiments, we find that training improves final-decision quality and induces emergent coordination in participation, speaker selection, and communication, even though the reward evaluates only the final decision.
We present LCM-Promo, an LLM-based uplift model for promotion allocation. LCM-Promo is a task-specific Large Commerce Model (LCM): a finetuned LLM trained on transactional commerce data to predict user intent and promotion response. It learns monotonic promotion-response curves from production logs by interpreting single-token outputs as conversion-threshold probabilities, while conditioning on session context such as day and delivery shift. In a production A/B test on churn reactivation, LCM-Promo increased conversion by 1% and reduced promotion cost by 6% relative to the Segment-EMA production baseline.
AI agents have made substantial progress in domains where they have a non-trivial amount of time to deliberate between actions, such as mathematics, software engineering, and performing tasks on desktop applications. It is less clear how such models fare in settings that demand real-time interaction, such as playing a video game or operating a physical device. In these settings, the environment state may evolve as the agent is reasoning, or even as the underlying model is performing a forward pass. To gain insight into the real-time interaction capabilities of vision-language agents, we introduce Gym-Anything-RT. Our key idea is to construct visual minigames that demand a portfolio of capabilities required for interactive real-time settings. Gym-Anything-RT uses an agentic pipeline to automatically generate such environments based on a taxonomy of six capabilities required for real-time interaction, including the ability to perceive the environment and act under an evolving environment state. A key feature of Gym-Anything-RT is that it allows for controlled comparison of real-time interaction capabilities: we can run the same minigame in real time, or pause or slow down the environment to relax the requirement for real-time actions. We use Gym-Anything-RT to construct 100 real-time minigames and evaluate AI agents on them. We find large capability gaps in real-time interaction. For example, GPT-6 Astra (xHigh) achieves a pass rate of only 9.0% on the real-time minigames, which rises to 75.0% when the environment is paused. We also identify intriguing behaviors by the most powerful frontier agents: for instance, when given the ability to write code, these agents write code that bypasses the need to perceive and act in real time. We publicly release Gym-Anything-RT and the generated minigames to spur further research on AI agents in real-time interactive settings.
Predictive maintenance is vital for commercial aviation, yet progress remains hindered by the lack of public, large-scale real-world datasets. As a result, most methods are developed and evaluated on proprietary data, limiting reproducibility. We introduce Pneuma, the first publicly available large-scale benchmark for predictive maintenance using onboard time series from in-service commercial aircraft. Built around bleed air systems, Pneuma contains over 920 million multivariate time steps across four aircraft types and 9 verified fault scenarios, directly aligned with real maintenance logs. The dataset exhibits key real-world challenges, including substantial class imbalance, subtle fault evolution patterns, and significant variance across aircraft configurations. We structure the benchmark around three tasks: multivariate forecasting, supervised fault classification, and unsupervised anomaly detection, with labels derived from actual maintenance records. Under unified settings, we evaluate over 25 models from four methodological families on 9 carefully curated subsets. The results reveal that even strong contemporary models struggle with subtle fault signatures. Further analyses show consistent gains from additional in-context examples and multivariate inference, while forecasting quality is strongly associated with anomaly detection performance. Together, these findings provide practical insights into effectively modeling complex real-world aviation time series. We hope Pneuma will serve as a rigorous and reproducible foundation for advancing data-driven predictive maintenance toward real-world deployment in commercial aviation.
Background. Selective prediction systems improve the safety of clinical artificial intelligence by deferring ambiguous cases to human experts while automating high-confidence decisions. However, this safety mechanism relies entirely on the premise that uncertainty scores accurately reflect clinical ambiguity. In prognostic tasks characterized by severe class imbalance, where the clinical outcome of interest is a minority, this assumption breaks down. Standard uncertainty measures cease to capture clinically aligned ambiguity; instead, they become a proxy for class membership, systematically penalizing minority patients regardless of their individual predictive clarity. Results. Across 56 synthetic conditions and three neurodegenerative cohorts spanning severe class imbalance to near-balanced conditions (multiple sclerosis, Parkinson's Disease, Alzheimer's Disease), our framework consistently maintained bounded, balanced risk across trajectories. In contrast, global metrics either collapsed minority Sensitivity or protected the minority at the expense of majority patients. Applying CCR with standard entropy fails to protect the minority because it breaks within-class monotonicity when tau=0.5. Combining CCR with threshold-aware metrics restores strict monotonicity, correctly identifies ambiguous patients, and safely mitigates minority exclusion. Conclusions. Under clinical class imbalance, standard uncertainty quantification measures dataset sparsity rather than clinical ambiguity, creating a systemic illusion of safety. This bias is a correctable structural flaw. Clinical pipelines deploying selective prediction under imbalance should adopt threshold-aligned uncertainty measures and class-stratified evaluation. This reduces class-specific risk imbalance, supporting safer selective prediction under the evaluated conditions without silently excluding the most vulnerable patients.
TechCrunch spoke to the MIT computer scientist charged with explaining OpenAI's latest mind-bending discovery
Label-free reinforcement learning with verifiable rewards (RLVR) rewards a language model for agreeing with its own majority vote. It improves reasoning at first but eventually collapses: the self-assessed reward goes to one while accuracy falls, often until the model gives the same answer to every problem. The collapse appears only when training uses many problems. We explain this dataset-size dependence as a collective instability. In a solvable many-problem model in which problems share parameters, a population whose problems prefer different answers amplifies any shared perturbation for as long as the population-averaged slope F'of the single-problem self-reinforcement drift F is positive. This holds while problems are still uncertain about their answers. Per-problem sharpening, slowed by 1/N for N training problems, races against the shared mode, which grows at a rate λ^2 independent of N, where λ is the strength of the shared coupling. This yields a critical number of problems N_c(1/δ)/(λ^2G), where δ seeds the shared mode and G decreases with the initial confidence. Simulations of the model confirm the predictions: a sharp transition, N_cλ^{-2} up to a logarithmic correction, a single critical amplification λ^2NG across couplings, confidence profiles and training variants, a logarithmic dependence on batch size, and no collapse for confident initial models. A kernel version of the theory identifies a protective coupling (generalization of sharpening) and a marginal-entropy bonus that stabilizes the uniform collective mode. In label-free RL of a small Transformer, removing the shared direction prevents collapse entirely, restoring it causes collapse, and collapse grows with training-set size and base-model entropy.
Seekable OCI (SOCI) indexing for Amazon SageMaker AI training and processing jobs takes full container image download off the critical path. SageMaker AI lazy-loads your image to start containers in seconds instead of minutes, with no changes to your job definition. See the benchmarks and how to adopt it.
Manipulation policies are evaluated predominantly by binary task success, which cannot tell whether the commanded gesture is the one the object's kinematics admit. We introduce Constraint-Referenced Strategy (CRS), which projects the commanded end-effector twist onto the object's joint axis, separating progress along the joint from off-constraint waste. CRS requires a joint model and a joint-following scripted controller derived from it, but no recorded demonstration or learned judge. On 74 simulated articulated objects, success registers three transfer failures as lower rates but attributes none, while the two CRS channels give each a distinct signature. A door-trained behavior-cloning policy opens drawers in 59 of 110 episodes, and in these passes it commands about 40the off-axis rotation of a drawer-trained policy's passes (1.27 vs.\ 0.032~rad/s). Relative to a scripted controller scored with the same axis, CRS verdicts are unchanged under joint-axis errors up to 30^; absolute thresholds tolerate about 8^.
NVIDIA RTX Spark is a new Windows PC platform for AI development, creation, and gaming in slim laptops and compact desktops. Powered by an NVIDIA Blackwell RTX...
Imitation policies that reliably execute most of a manipulation trajectory can still fail in localized regions requiring last-mile precision. Updating the full policy or exploring residual actions everywhere treats this local failure as a global learning problem. We introduce Adaptive Residual Correction (ARC), a lightweight post-training module that uses reinforcement learning (RL) to learn a residual correction on top of a frozen policy while using sparse human corrections to structure autonomous exploration. Rather than treating human corrections as imitation targets, ARC uses pre-intervention states to determine 'when' residual control should become active and correction geometry to determine 'where' in residual action space autonomous refinement should explore; task reward determines 'what' residual is ultimately executed. Across three precision-manipulation tasks on a real robot, ARC improves average task success from 33.3% to 75.0%. The human corrections define task-dependent 2-3 dimensional subspaces of the seven-joint residual space that retain 96.0-97.7% of squared correction magnitude. Together, these results show that sparse human corrections can localize and constrain autonomous post-training without requiring the observed correction itself to serve as the final action target.
Multi-view or video diffusion models have recently emerged as state-of-the-art approaches for novel-view synthesis from sparse image collections. While they can produce high quality images, they tend to hallucinate unrealistic spatial layouts when synthesizing views outside the input views (scene extrapolation). We propose to address this challenge for outdoor scenes by using satellite images as an additional information source to condition the multi-view generative model. We introduce a new satellite-conditioned multi-view diffusion model that combines conditioning from a satellite image and street-level input images when generating novel-views. Our cross-attention based conditioning allows us to retain pretrained multi-view diffusion priors to generate seamless, realistic, novel views from a handful of source views, while also adhering to the scene layout as seen from satellite images. Our model does not use 3D scene reconstruction, and only relies on posed street and satellite views. Our experiments on outdoor datasets show that our model is better than both satellite-conditioned or street-view conditioned baselines on novel-view synthesis, especially on challenging cases where target views have very little overlap with source views. Project page: https://nianticspatial.github.io/groundcontrol
Failure diagnosers for robot manipulation are increasingly vision--language models (VLMs), trained and evaluated on single-arm failures produced by perturbing a successful demonstration. Bimanual tool use adds failures of other kinds: a tool that slips out of its socket while still held, two correct gestures made at different times, and attempts that fail for two reasons at once. On a simulated bimanual tool-use task whose failure causes are read from the recorded trace, we measure what each sensing channel lets a diagnoser tell. The tool's slip is read on the tool hand; which hand was late is read on both arms, while a sensor on one hand reads its own hand's delay and at most part of the other's; and whether a late attempt was also pushed too weakly is not identifiable from passive sensing when the tool hand is late. Within two attempts, a repair policy that escalates when the cause is not identifiable repairs as many failures as one told the true cause. A VLM's internal state carries the late hand almost perfectly, along a direction no closer to the one its answer reads than a random one; whether the answer reports it depends on the wording of the question.
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.
Anthropic wants to have it both ways. With its impending IPO, it wants to tap the vast riches of the public markets and insists it…
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.
Self-attention mechanisms have established the Transformer as the dominant backbone across natural language processing, source code intelligence, and automated theorem proving. However, all-to-all pairwise token comparison enforces a quadratic {O}(N^2) compute and memory barrier alongside severe softmax attention dilution as sequence length N scales beyond the training horizon. Inspired by recent advances in algebraic graph learning (WPNet), this work introduces GTFormer, a syntax-free hierarchical Graph Neural Network (GNN) that replaces flat self-attention for general long-context sequence modeling. GTFormer organizes raw token streams into a bounded-degree hierarchy combining a balanced binary reduction tree (_2 N depth), horizontal boundary-bridging shift edges, random expander shortcuts, multi-channel convex highway gating, and a top-down broadcast pass. Across eight long-context code, log, and multi-hop retrieval benchmarks trained exclusively on sequences of length N 512, GTFormer extrapolates zero-shot to N = 4{,}194{,}304 (8192) on a single commodity GPU in linear {O}(N) memory, maintaining near-perfect accuracy where standard and RoPE Transformers suffer from out-of-distribution attention collapse and out-of-memory exhaustion.
