Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
Intent misinterpretation during vehicle interactions causes recurring planning failures. We study a decision layer in which a language-guided intent module reads structured descriptors, computes a smo...
Answer accuracy is an insufficient reliability signal for LLM data agents. In structured-data tasks, a benchmark-correct answer can be produced by an invalid trace. This paper introduces Trace Integri...
Robust Markov Decision Processes (RMDPs) generalize classical MDPs by allowing uncertainty in transition probabilities and optimizing against their worst-case realization. We consider $(s,a)$-rectangu...
Traffic Anomaly Understanding (TAU) requires models and systems to detect, reason about, and explain anomalous events in transportation videos. To address this challenge, we propose TAU-Agent, an agen...
Large Language Models (LLMs) exhibit strong problem-solving abilities, positioning them as promising agents for Socratic teaching to guide students through step-by-step heuristic questioning. However,...
In serious illness, human surrogates often struggle to accurately predict patient preferences (68% accuracy), causing decision conflict. Personalized Patient Preference Predictor (P4) agents offer a p...
The Meteosat Third Generation (MTG) Flexible Combined Imager (FCI) offers new opportunities for tropospheric temperature and humidity profiling, at higher spatio-temporal resolutions and expanded spec...
Automated root cause analysis (RCA) with large language models (LLMs) has drawn growing attention. Today, SREs typically automate RCA with LLMs in one of two ways: directly using a general-purpose age...
The article "How to Effectively Solve 100+ Tasks with Claude Code" discusses strategies for working more efficiently with coding agents. It focuses on practical approaches to manage and complete a large number of tasks using Claude Code. The post was originally published on Towards Data Science.
The article highlights Paul Dix’s astonishment that AI was able to generate one million lines of code and then refine it over several months into a reliable software product now used by millions of developers. Dix argues that this achievement is far more impressive than merely translating code between languages, emphasizing that with a verification system and clear guidance, AI can produce and iteratively improve highly complex, sophisticated software until it functions perfectly.
The article titled "Is Agentic AI Just Automation?" argues that many so‑called agents are merely flowcharts in disguise. It explains why this misconception exists and suggests what kinds of systems should be built instead to achieve true agentic AI.
arXiv:2608.22075v2 Announce Type: replace-cross Abstract: Adversaries now move faster than manual response processes can absorb. The average eCrime breakout time, that is, the interval between initia...
The paper introduces rebuild‑dossier, an open‑source tool that locks an application’s real interface before code is written and enforces one‑test‑at‑a‑time building through automated checks. In experiments, a compliant agent failed a held‑back test while a rule‑breaking agent passed, showing that a passing test suite can be gamed. The study also demonstrates that the automated check mechanism, rather than interface‑locking alone, is crucial for reliable rebuilds, and that multi‑level verification catches errors that single‑level checks miss.
The paper introduces Evidence-Carrying Termination (ECT), a method that allows tool‑using large language model agents to declare a task complete only when a typed certificate links every required answer claim to valid, in‑scope trace evidence and a deterministic replay confirms the claimed value. In controlled experiments across 48 synthetic tasks and 576 trajectories, ECT eliminated unsafe completions and premature unsupported terminations, outperforming existing termination critics and controllers while maintaining comparable supported completion rates.
The paper reviews the evolution of object‑counting techniques from class‑specific density regression to open‑vocabulary, foundation‑model‑backed counters that can handle visual and textual prompts. It highlights that current evaluation relies on a few saturated benchmarks, leading to models exploiting statistical regularities rather than true generalization. The authors propose a five‑axis taxonomy and audit the literature across domains such as microscopy, remote sensing, crowd counting, and agriculture, identifying six structural contradictions and outlining a roadmap for robust, multimodal evaluation protocols.
The paper introduces a new framework for analyzing multimodal data—visual, auditory, and spatial—by focusing on the complexity of embodied perception and interaction in dynamic, naturalistic settings. It expands upon prior visual complexity work to categorize diverse attributes (quantitative, structural, dynamic, auditory, interactional) that together describe multimodal complexity. The authors illustrate how this model can characterize visuospatial complexity in everyday driving and suggest its use for creating and evaluating benchmark datasets that prioritize cognitive human factors.
LUCAID is an agentic multimodal AI system designed for precision lung cancer pathology, integrating nine modules that cover the entire routine workflow—from quality control and tumor detection to histological subtyping, microenvironment profiling, cellularity quantification, and biomarker scoring (PD‑L1, MET, TROP‑2). The system generates automated structured reports and allows interactive querying of module outputs. In prospective clinical validation, LUCAID achieved 93.0% concordance with an expert‑panel reference standard for clinically actionable decisions, outperforming five experienced thoracic pathologists who ranged from 68.3% to 81.1% concordance.
The paper introduces DoublesEval, a diagnostic framework that uses professional doubles badminton to test visual‑language models’ ability to reason about dynamic multi‑agent interactions. It decomposes rallies into key moments and evaluates models across four dimensions—atomic recognition, intra‑segment composite understanding, cross‑segment causal reasoning, and high‑level tactical abstraction—highlighting specific reasoning failures. The authors also propose TacticCheck, a lightweight consistency checker that improves performance without retraining the models, yet significant gaps remain in tactical reasoning.
EgoErrorVQA introduces a new egocentric visual question answering task that evaluates visual agents’ ability to detect procedural errors in everyday activities. The paper presents an evaluator agent built on the Agent2Agent protocol and shows that current models struggle with procedural error recognition. It also proposes Ego-ADR, an Adaptive Decoupled Reasoning framework that improves performance on the task, achieving state‑of‑the‑art results.
The paper introduces a multi‑agent framework that lets large language models (LLMs) perform controlled experiments using scientific simulation models, specifically for pharmaceutical process design. Given a user query and baseline configuration, the system builds a structured task, designs and runs comparative simulations, interprets outcomes, and generates evidence‑based recommendations for optimizing process parameters. By integrating high‑fidelity simulations with LLMs, the approach yields more specific, actionable outputs and improves user‑rated correctness and helpfulness compared to language‑only reasoning.