Translate
Live intelligence

Latest AI updates

573 updates
AllModelsProductsIndustryResearchTutorialOpinion
Research Editor selected

Kierston & KierstonBench: Simulated City Benchmark for AI in Crime Investigation

The paper introduces Kierston, a city-scale simulation of Allentown, PA, and KierstonBench, a benchmark for evaluating language models in crime investigation and surveillance tasks. It generates realistic records from a common behavioral timeline and tests models on 32 task families. Evaluation of 16 models shows most fail, while a few frontier models solve most tasks but still fall for deceptions.

Why it matters: Provides a novel, concrete benchmark for a critical AI application area, with clear evaluation results and practical implications.

arxiv1d agoScore 85
AI safetycriminal investigationlanguage model evaluation
Research

ReSI-Math: Recoverable Capability Frontiers for Efficient Reasoning Improvement

ReSI-Math is a framework that identifies recoverable reasoning failures in LLMs—cases where direct decoding fails but trajectory-level search can elicit correct solutions—and converts them into efficient RLVR supervision. Using self-judge-guided evolutionary search, it selects frontier problems for sequential RLVR stages. On Qwen3-VL-8B, it improved MATH500 and WE-MATH averages from 78.71 to 80.16 after three stages, and frontier-guided selection outperformed random selection in matched single-problem RLVR.

arxiv1d agoScore 78
reinforcement learningLLM reasoningdata efficiency
Research

Density-Aware Reward Scaling for Diverse High-Reward Outcomes in RL

DARS is a lightweight reward-processing method that inversely scales rewards by local outcome density to promote reward-proportional sampling in continuous spaces. It requires no learned density model or auxiliary objective)Skip, and works with standard policy-gradient training. In multimodal navigation and text-to-image prompt adaptation, DARS-GRPO avoids mode collapse and improves diversity while maintaining semantic alignment.

arxiv1d agoScore 78
Reinforcement LearningReward DesignDiversity in AI
Research Editor selected

Dependence-Aware Belief Propagation for Unsupervised Truth Discovery Among Correlated AI Agents

This paper introduces BP-TD, a method for truth discovery among LLM agents that accounts for correlated errors from shared base models. It uses per-agent decorrelation weights in mean-field variational inference, outperforming majority vote on MMLU without labels and ranking agents by true accuracy. The method's benefit depends on the pool composition, and with a few labels, selecting the best agent beats all aggregators tested.

Why it matters: Provides a concrete, novel algorithm with empirical results addressing a practical problem of correlated AI agents, valuable for AI system design and evaluation.

arxiv1d agoScore 85
AI agent reliabilityEnsemble methodsVariational inference
Research Editor selected

Asymptotic Optimality of cμ-Rule for LLM Inference Scheduling under Memory Constraint

This paper studies LLM inference scheduling as an online queueing problem with finite KV-cache memory. The authors develop a fluid model that reduces the system to a multiclass single-server queue and derive a cμ priority rule where effective service rates account for computation, memory access, and memory capacity. They prove the rule minimizes cumulative holding cost in the fluid model and, for finite workloads, also minimizes completion time and maximizes output-token throughput. Experiments on an NVIDIA H800 show practical implementations reduce average latency while maintaining high throughput.

Why it matters: Provides a rigorous theoretical foundation and practical validation for a scheduling policy that improves LLM inference efficiency under memory constraints, directly relevant to serving systems.

arxiv1d agoScore 85
LLM inference optimizationqueueing theorymemory management
Research

RAHC: Rule-Augmented Hyper-Relational Knowledge Graph Completion for Materials Synthesis

RAHC is a new framework for completing missing synthesis conditions in materials science by augmenting hyper-relational knowledge graphs with rules extracted from training data and literature. It handles both single-slot and joint multi-slot completion, using hard rules for validity constraints and soft rules for ranking, with gated fusion of structural and rule evidence. Experiments on five materials datasets show up to 15.6% MRR gains over MAYPL in semi-inductive settings and improved performance on the ILPC'22 Small benchmark.

arxiv1d agoScore 78
Knowledge Graph CompletionMaterials InformaticsRule-Augmented Models
Research Editor selected

AgenticFinBench: Benchmarking Financial Agents on Diverse Real-World Tasks

AgenticFinBench introduces a benchmark of 230 real-world financial tasks across 8 categories, 2 languages, and 4 complexity levels, with a reference-free evaluation framework that audits hallucinations. Experiments across 18 agent configurations show hallucination auditing lowers the baseline leader's score by 7.58 points, and harness differences explain more variation in evidence grounding than model differences. The benchmark aims to advance financial reasoning and factual verification for reliable agent responses.

Why it matters: Provides a concrete, recent benchmark with novel evaluation methodology and actionable findings for financial AI agents, useful for researchers and practitioners.

arxiv1d agoScore 82
financial AIagent evaluationhallucination auditing
Research Editor selected

LoCo: Local Preference Learning for Reasoning Compression

LoCo is a new method that reduces the inference cost of large reasoning models by learning when to stop reasoning. It detects overthinking states, regenerates shorter verified continuations, and trains with DPO on state-conditioned preference pairs. On math and code benchmarks, LoCo cuts completion length by up to 45% while maintaining or improving accuracy, and transfers from math to code.

Why it matters: This paper presents a concrete, novel technique with strong empirical results and cross-domain generalization, offering practical value for reducing AI inference costs.

arxiv1d agoScore 82
reasoning modelsinference efficiencypreference learning
Research Editor selected

Natural Textual Unlearnable Examples for Large Vision Language Models

This paper introduces the first unlearnable example (UE) method specifically for large vision-language models (LVLMs), called Natural Textual Unlearnable Examples (NTUE). NTUE perturbs image labels subtly to create a shortcut between an identity and a target, misleading LVLMs without adding misinformation or harming readability. Experiments show NTUE outperforms traditional UE methods, achieving high success with a poison rate as low as 5%.

Why it matters: Provides a novel, practical defense against data misuse in multimodal AI, with concrete results and a low poison rate, valuable for privacy and security.

arxiv1d agoScore 82
Large Vision Language ModelsUnlearnable ExamplesData Privacy
Research Editor selected

PaySeqGen: Interpretable Inverse Reinforcement Learning for Fraud Sequence Generation

PaySeqGen is an interpretable inverse reinforcement learning framework that reconstructs fraud behavior policies from observed payment trajectoriesholistically, generating new fraud sequences for detector augmentation. It learns interpretable behavioral rewards capturing fraudsters' preferences across transaction contexts)Skip, and experiments at Ant International show it outperforms state-of-the-art generative augmentation methods. The framework also enables reward-based trajectory analysis to identify multistep fraud tactics in real payment systems.

Why it matters: This paper presents a novel application of inverse RL to payment fraud, with real-world deployment and interpretability benefits, offering practical value for fraud detection and analysis.

arxiv1d agoScore 82
fraud detectioninverse reinforcement learningpayment security
Research

UniFlow: Unified Multi-Scale Flow Matching for Time Series Generation

UniFlow is a new framework for time series generation that integrates multi-scale representation learning with non-autoregressive generation via a shared-semantic discrete interface. It uses a multi-scale tokenizer with shared-index voting to consolidate temporal information into a single public-ID sequence, and geometry-aware categorical flow matching to generate these IDs efficiently. Experiments on four benchmarks show improved fidelity, cross-scale consistency, and faster inference than autoregressive and diffusion baselines.

arxiv1d agoScore 78
time series generationflow matchingmulti-scale representation learning
Research

Feeling of Knowing in Large Language Models

This paper introduces a functional 'feeling of knowing' (FoK) mechanism for LLMs to align answerability judgments with post-training knowledge updates. It proposes two trainable channels—knowledge and FoK—trained via three stages: on-policy supervised fine-tuning, knowledge-delta FoK training, and FoK-guided policy optimization. Experiments on factual QA and sequential updates show improved judgment quality without sacrificing capability on MMLU and ARC-Easy.

arxiv1d agoScore 78
LLM alignmentknowledge judgmentmodel routing
Research Editor selected

HTCE: Topological Cross-Scene Experience Reuse for Object Navigation

HTCE is a homeomorphism-inspired framework that canonicalizes and reuses navigation experience across scenes for embodied object-goal navigation. It compresses stored route descriptions by 17.7–23.6% without performance loss and achieves state-of-the-art success and SPL on HM3D and MP3D benchmarks under a frozen vision-language policy. The method improves success rate by up to 4.9 points and SPL by up to 2.8 points.

Why it matters: This paper presents a novel topological approach to experience reuse in embodied AI, with concrete benchmark gains and open-source code, offering practical value for navigation research.

arxiv1d agoScore 82
Object Goal NavigationTopological LearningExperience Reuse
Research

Searched Intrinsic Rewards Transfer but Are Tamperable by a Shortcut

This paper investigates whether intrinsic rewards found by evolutionary search over generic event combinations can transfer to unseen tasks and resist exploits absent during search. The CMA-ES-selected reward beat task-only PPO and random-search reward on a held-out task, but a hand-wired reward with task-specific events performed better. A free reset action, not present during search, collapsed learning, showing selection gave no protection against such exploits.

arxiv1d agoScore 78
Intrinsic reward searchReinforcement learning transferReward tampering
Research

DGC-Net: Cross-Modal Dynamic Routing with Global-Guided Compensation in Multimodal Sentiment Analysis

DGC-Net is a new network for multimodal sentiment analysis that addresses cross-modal affective cue inconsistency and global-local contribution imbalance. It uses cross-modal contribution-aware dynamic expert routing with global contexts to guide local expert selection, and global-guided dynamic compensation fusion to adaptively combine global semantics with refined local cues. Experiments on five multimodal benchmarks show effectiveness and general applicability.

arxiv1d agoScore 78
Multimodal Sentiment AnalysisDynamic GatingGlobal-Guided Compensation
Research Editor selected

MambaPFN: Amortized Nonlinear Variable Selection with Prior-Data Fitted Networks

The paper introduces MambaPFN, a Transformer-based method for model-agnostic variable selection that identifies variables with nonlinear dependence on a response. It uses a functional-mapping perspective, pretraining on generated data to learn posterior inclusion probabilities, then applies to new datasets without updates. Experiments show strong performance, including a scaling law and a 20% improvement over baselines on a Facebook comments dataset.

Why it matters: Presents a novel, concrete AI method with empirical gains and scaling behavior, useful for researchers and practitioners in interpretable ML.

arxiv1d agoScore 82
variable selectionTransformer architecturesamortized learning
Research Editor selected

GroupAssistBench: Benchmarking Real-World Group Memory Assistance Beyond Recall

GroupAssistBench is a new benchmark for evaluating memory use in group assistance, built from real-world group conversations with a deployed assistant, covering 80,299 messages across 50 groups. It tests both recall (L1) and use (L2) with service requests lacking fixed answers, across single, distributed, and conflicting memories. Evaluations show frontier models and memory systems lag on use, especially for distributed and conflicting memories, but adding retrieval-relation and constraint-binding techniques improves performance.

Why it matters: This introduces a novel benchmark addressing a gap in AI memory evaluation, with real-world data and actionable insights for improving group assistant systems.

arxiv1d agoScore 85
AI memorygroup chat assistantsbenchmarking
Research Editor selected

ScamWorld: Interactive Environment for Evaluating Web Agents Against Online Fraud

ScamWorld is a new interactive environment that reconstructs reported scam websites to test how web agents handle online fraud. In tests with six frontier LLMs, baseline deception rates ranged from 11% to 35%, with agents more likely to proceed with payments than with credential or wallet requests. The environment enables controlled, repeatable evaluation of agent behavior against real-world fraud scenarios.

Why it matters: Provides a concrete, novel testbed and empirical results on LLM-based web agents' vulnerability to online fraud, directly relevant to AI safety and agent evaluation.

arxiv1d agoScore 85
AI safetyweb agent evaluationonline fraud