Translate
Automated AI newsroom

AI News

High-signal AI developments, independently scored, summarized and organized for fast reading.

Live intelligence

Editor-selected AI developments

330 updates
AllModelsProductsIndustryResearchTutorialOpinion
Research Editor selected

GeoFaham: Multi-Agent Geospatial Analytics for Disaster Response

GeoFaham is a domain-specialized multi-agent system that decomposes geospatial disaster-response workflows into specialist agents for vector, map, imagery, and raster analysis, coordinated by an Orchestrator with a dual-ledger control loop. It uses a Response Store to persist outputs outside the LLM context, reducing token usage. On the new GeoFaham-Bench benchmark, it outperforms general coding agents with a score of 0.940 versus 0.879, using 7.5 times fewer tokens.

Why it matters: Introduces a novel multi-agent architecture and benchmark for geospatial AI, showing significant efficiency and accuracy gains over strong baselines.

arxiv1d agoScore 88
multi-agent systemsgeospatial analyticsdisaster response
Research Editor selected

ALBI: LLM-Guided Inductive Logic Programming via Iterative Generate-Test-Constrain Refinement

ALBI is a neuro-symbolic ILP framework that replaces the ASP-based hypothesis generator in the Learning from Failures paradigm with an LLM, while using SWI-Prolog as a formal verifier. It implements an iterative generate-test-constrain loop where the LLM proposes hypotheses, Prolog tests them, and diagnostic feedback drives refinement. On 30 standard ILP benchmarks, ALBI achieves 100% success across three frontier LLMs, matching Popper with only 1.4-1.7 iterations on average. Semantic anonymization tests confirm robust symbolic reasoning, with all models maintaining 100% success despite a moderate increase in iterations.

Why it matters: This paper presents a novel integration of LLMs with formal verification for ILP, demonstrating high success and robustness, which is valuable for researchers and practitioners in neuro-symbolic AI.

arxiv1d agoScore 82
Inductive Logic ProgrammingLarge Language ModelsNeuro-symbolic AI
Research Editor selected

Geometric Abstraction Reduces Multimodal Queries in Agentic Robot Policies

This paper proposes replacing step-by-step visual reasoning in multimodal robot policies with a 3D geometric abstraction that converts scene geometry into typed, evidence-aware symbolic references grounded from RGB-D data. The system refreshes metric values locally and returns compact textual checkpoints after each action, invoking direct visual reasoning only on demand. Experiments show improved multi-step manipulation completion while substantially reducing repeated multimodal queries.

Why it matters: Offers a concrete method to improve efficiency and reliability of agentic robot policies by using geometric abstraction, relevant to AI-driven robotics.

arxiv1d agoScore 85
robot manipulationmultimodal language modelsgeometric reasoning
Research Editor selected

FloMo: 3D Scene Flow as a World Action Model Intermediate for Learning from Human Video

FloMo is a 5B video-generation model fine-tuned to predict 3D scene flow and action tokens, using scene flow as an intermediate representation to transfer video pretraining to robot action prediction. Co-trained on human video and robot teleoperation data, it generalizes to unseen objects and tasks, outperforming video prediction objectives. Experiments show that predicting video wastes model capacity, as action tokens attend more to motion than video.

Why it matters: This paper presents a concrete, recent AI development with empirical evidence that 3D scene flow improves sample efficiency and generalization in robot learning from video.

arxiv1d agoScore 85
Robot learningVideo pretrainingScene flow
Research Editor selected

RFWorld: Rollout-Free World Model for End-to-End Autonomous Driving

RFWorld introduces a rollout-free world model for trajectory evaluation in end-to-end autonomous driving. It builds a shared scene memory and uses lightweight training-time temporal readout with semantic supervision to create future-readable representations, avoiding costly recursive rollout. At inference, candidates query the memory via sparse spatial readout, cutting computation and improving planning-aligned representation, achieving SOTA on NAVSIM and Bench2Drive.

Why it matters: This is a concrete research advance that reduces inference cost and improves trajectory evaluation accuracy, with benchmark results on standard driving datasets.

arxiv1d agoScore 85
end-to-end planningworld modelstrajectory scoring
Research Editor selected

LatentTriad: Pre-Action Risk Representations for Malicious Agent Skill Detection

LatentTriad is a new method that detects malicious skills in LLM agents without executing them, using hidden states from a single prefill pass. It combines contextual boundary features, group-adjusted operation directions, and departures from benign state relationships to achieve 99.0-99.2% pooled F1 across 5,830 skill packages. The method is execution-free, producing no output tokens and invoking no tools, with a compact implementation running in 259-284 ms median.

Why it matters: This paper presents a concrete, recent AI safety technique with strong empirical results and practical efficiency, valuable for developers and researchers working on agent security.

arxiv1d agoScore 85
AI safetyLLM agentsmalicious skill detection
Research Editor selected

Molecular Prior Networks: Single-Pass Affinity Prediction via Transformers

The paper introduces Molecular Prior Networks, a transformer-based model that predicts drug-target affinity in a single forward pass, trained on thousands of existing affinity datasets. It matches state-of-the-art performance on the FS-Mol regression benchmark for small support sets while being faster due to no task-specific training. Comparisons show the model's performance goes beyond simple molecular similarity.

Why it matters: Presents a novel AI method for drug discovery with concrete benchmark results and practical speed advantages.

arxiv1d agoScore 82
drug discoverymolecular modelingfew-shot learning
Research Editor selected

Workload-Static Optical Circuit Switching for Scalable LLM Inference Decode

This paper proposes using workload-static optical circuit switching (OCS) for LLM inference decode, exploiting the fixed communication structure of decode to pre-configure circuits per deployment. Co-designed with model parallelism and topology-aware collective schedules, the approach turns spare accelerator ports into fewer communication phases or higher bandwidth. Evaluations on a 576-accelerator scale-up domain serving 5T-parameter MoE models show up to 65% better interactivity and 119% better energy efficiency over oversubscribed packet-switched fabrics.

Why it matters: Offers a concrete, novel networking architecture for LLM inference with significant measured gains, relevant to scalable AI systems.

arxiv1d agoScore 85
LLM inferenceoptical networkingmodel parallelism
Research Editor selected

AI-Mediated Proposals Show Instability and Hidden Alternatives in Collective Decision-Making

A study of four LLM mediators found that proposals generated from citizen opinions are unstable: re-running with different seeds or order changes assignments in 17-20% of cases, and reordering opinions affects assignments nearly as much as replacing them. Human annotators confirmed real differences, though an LLM judge overestimated frequency. Variation persists even with safeguards like temperature zero, and prompts seeking agreement underrepresent minority views. The authors propose audits to expose alternative assignments and disclose the objective behind each proposal.

Why it matters: This research reveals a concrete, practical risk in AI-mediated collective decision-making, with actionable audit recommendations for transparency.

arxiv1d agoScore 85
AI-mediated deliberationLLM reliabilitytransparency
Research Editor selected

Meta$^2$: Precomputing Reusable Knowledge for Online Harness Evolution in Long-Horizon Agents

Meta$^2$ is a new method that precomputes reusable knowledge for evolving agent harnesses (prompts, tools, memory, hooks) online during long-horizon tasks. It learns a textual Meta-Skill offline by contrasting training rollouts with and without privileged verifier information, then applies this knowledge online to decide whether to keep or evolve the harness per task. On Terminal-Bench 2.1 and DeepSWE 1.1, it achieves 81.00% and 44.44% with GPT-5.6-Terra, outperforming baselines.

Why it matters: This paper presents a novel approach to harness optimization that combines offline learning with online adaptation, showing strong benchmark results and addressing a key limitation of existing methods.

arxiv1d agoScore 85
agent harness optimizationmeta-skill learningonline evolution
Research Editor selected

Query Routing Enables Power Flexibility in LLM Datacenters

This paper proposes using query routing across LLM instances to provide power demand flexibility in datacenters without deferring requests. The authors develop an analytical framework linking query arrival rates and sequence lengths to token iteration time, residence time, capacity, and power, validated on four GPU platforms with 2.8% mean absolute error. A trace-driven simulation of a 10,000 H100 GPU datacenter shows up to 16% total power flexibility, with 90% of desired reduction achieved in ~10 seconds.

Why it matters: Provides a concrete, validated mechanism for datacenter power flexibility, directly addressing the growing energy demands of LLM inference.

arxiv1d agoScore 82
LLM inferencedatacenter power managementquery routing
Research Editor selected

WebCatalyst: High-Fidelity RL for Interactive HTML Generation

WebCatalyst is a reinforcement learning framework that improves interactive HTML generation from natural-language specs, using a game-level GUI assessor, Visual Anchor to prevent reward hacking, and Action-Trace Credit for token-level credit assignment. Trained on under 1K requests, it raises Cookie-Bench Mini Games from 68.8 to 75.3 and WebGen-Bench accuracy from 48.8 to 56.9 on Qwen3.6-35B-A3B, outperforming Claude Opus 4.7 in average rank. The work highlights feedback fidelity as key to advancing interactive HTML generation.

Why it matters: Provides a concrete, novel RL method with measurable benchmark gains and analysis, valuable for AI researchers and practitioners in code generation.

arxiv1d agoScore 82
WebCatalystinteractive HTML generationreinforcement learning
Research Editor selected

Asynchronous Robot Policy decouples VLM reasoning from fast action control

ARP is an architectural framework that separates high-capacity VLM semantic reasoning from lightweight action generation using asynchronous processes at different frequencies. It updates a semantic memory at low frequency while a Vision-Action Expert generates actions at high frequency, trained to handle staleness and execution delay. On Franka tasks, ARP improves success rate by 18%, reduces execution time by 20%, and achieves 3-5x baseline performance in dynamic simulations, while allowing the VLM to run at 10x lower frequency without significant loss.

Why it matters: This is a concrete architectural advance addressing the latency-reactivity tradeoff in VLA robots, with clear quantitative gains and practical efficiency benefits.

arxiv1d agoScore 85
robot manipulationvision-language-action modelsasynchronous processing
Research Editor selected

RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On

RoboTryOn converts egocentric human videos into robot demonstration videos by swapping the human for a target robot while preserving the task, objects, and background. It uses autoregressive keyframe translation and motion conditioning on human hand skeletons, plus an inverse dynamics model with depth features to infer actions. Policies trained on this synthetic data improved success rates on novel bimanual tasks from 2% to 60% without real robot demos, and matched teleoperation-trained performance at about a third of the collection cost.

Why it matters: This paper presents a novel, cost-effective method for generating robot training data from human videos, with strong experimental results, making it valuable for robotics and AI research.

arxiv1d agoScore 88
Robot foundation modelsImitation learningData augmentation
Research Editor selected

BREM-NET: Multimodal Neural Model Separates Behaviorally Relevant Dynamics

Researchers introduce BREM-NET, a nonlinear multimodal dynamical model that integrates behavior with multiple neural modalities like spiking activity and local field potentials. It separates behaviorally relevant from residual neural dynamics during inference, improving behavior decoding, neural prediction, and latent alignment with behavior. The model remains robust to asynchronous modalities and dropouts, addressing real-world recording challenges.

Why it matters: This presents a concrete new AI model with demonstrated improvements on a public dataset, offering practical value for neuroscience and brain-computer interface research.

arxiv1d agoScore 82
neural data fusionbrain-behavior modelingmultimodal learning
Research Editor selected

AgentAM: LLM Agent for Spatter- and Defect-Aware Process Optimization in Laser Powder Bed Fusion

AgentAM is an LLM agent that provides natural-language access to CFD-trained surrogate models for laser powder bed fusion (LPBF), enabling process engineers to query spatter and melt pool predictions without programming. The surrogates achieve high accuracy (R² ≥ 0.95 for melt pool, 0.83 for spatter) and defect classification matches simulated geometry in 93.4% of tracks. The agent successfully handles prediction, process-window scans, and constrained optimization, with margin-aware optimization improving robustness to process drift. A 145-prompt benchmark shows 98.5% parsing accuracy and faithful reporting.

Why it matters: This paper presents a concrete AI agent that bridges advanced predictive models with practical shop-floor use, demonstrating measurable performance improvements and a novel benchmark.

arxiv1d agoScore 85
AI agents for manufacturingsurrogate modelingprocess optimization
Research Editor selected

OperAItor: Agentic Framework for Fault-Tolerant Chemical Process Operation

OperAItor is an open-source framework for building and evaluating LLM agents that supervise fault management in chemical plants. Tested on a simulated reactor-distillation process, it integrates monitoring, diagnosis, knowledge retrieval, and action planning with multiple validation methods. Across 20 fault scenarios, validated agents reduced plant stops from 18 to 5-8 and recovered $265,000 of potential losses.

Why it matters: Provides a concrete, reproducible benchmark and demonstrates measurable economic value of LLM agents in industrial process control.

arxiv1d agoScore 82
agentic AIindustrial AIfault diagnosis
Research Editor selected

Fairness Metrics based on the AUC in Clinical Predictive AI

This paper examines eight AUC-based fairness metrics for clinical prediction models, highlighting that the AUC is non-collapsible, so subgroup and overall values are not directly comparable. The authors characterize each metric's estimand, relate them to the decomposition of overall AUC, and use EuroSCORE II simulations to illustrate behavior. They recommend within-group AUC parity and caution against gap-to-overall, equity-scaled, and minimum-based metrics.

Why it matters: Provides a critical evaluation of fairness metrics with practical recommendations for clinical AI, directly useful for model developers and researchers.

arxiv1d agoScore 82
fairness in AIclinical predictive modelsAUC decomposition