Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2507.05723v1 Announce Type: cross Abstract: The emergence of Large Language Models (LLMs) with increasingly sophisticated natural language understanding and generative capabilities has sparked...
arXiv:2610.27157v1 Announce Type: cross Abstract: Inference-time harnesses, i.e., external procedures that call a model many times and keep state across calls, can substantially improve model capabil...
arXiv:2610.28409v1 Announce Type: cross Abstract: Large language model agents are often given an inference budget and asked to maximise success within it. A multi-turn agent has to allocate this budg...
The paper introduces Gibson, a virtual environment designed to develop real‑world perception for active agents. Gibson virtualizes real spaces, containing over 1,400 floor plans from 572 buildings, and includes a synthesis mechanism called "Goggles" that allows models trained in simulation to be deployed directly in the real world without additional domain adaptation. The environment also embeds agents within realistic physics and spatial constraints to support embodied learning.
arXiv:2609.34540v2 Announce Type: replace Abstract: Ontology Learning (OL) from text has advanced with the emergence of Large Language Models (LLMs), but it remains challenging due to the limited ava...
arXiv:2610.26636v2 Announce Type: replace Abstract: Code generation models are increasingly used to produce interactive artifacts, such as websites and user interfaces. Many properties that determine...
The study examines whether a one‑hour adaptive interview can reveal a person’s value‑laden decision policies to a large language model (LLM). Forty‑six adults underwent the interview and later answered 25 dilemma questions; the researchers compared predictions from various transcript segments, adaptive versus fixed follow‑ups, and a baseline model with no personal data. Results show that no part of the interview reliably predicts the participants’ answers better than the baseline, and adaptive follow‑ups offer no advantage over fixed ones, though the transcripts do help recover the participants’ MBTI types.
DataPraxis is a framework that scales analytics tasks by evolving verified workspaces, progressively adding validated findings and artifacts to uncover deeper questions. It constructs tasks from these enriched workspaces, ensuring analytical results are verified throughout the process. Using this approach, the authors created a 5,000‑trajectory dataset (DataPraxis‑5K) and trained large models (DataPraxis‑27B and DataPraxis‑35B‑A3B) that achieve competitive performance on benchmark tasks such as DABStep and JobBench.
arXiv:2610.28467v1 Announce Type: new Abstract: Human mobility data are fundamental to Web-based location services and broader urban applications, and mobility generation provides synthetic trajector...
arXiv:2610.27205v1 Announce Type: cross Abstract: Web agents are typically evaluated on English-language interfaces, leaving their ability to operate across the world's multilingual websites largely...
arXiv:2610.27735v1 Announce Type: new Abstract: Recursive self-improvement, in which frontier AI models work on training the next generation, is quickly becoming a reality. However, the safety of thi...
The paper introduces AuthorizationBench, a benchmark designed to evaluate whether large language model (LLM) agents act within the scope of user authorization when acting on their behalf. The benchmark comprises 286 executable tasks across ten application domains, covering situational triggers, presence or absence of direct harmful consequences, and varying reasoning effort. In experiments with four models and multiple agent harnesses, agents violated authorization in 19.2% of trajectories, with rates ranging from 10.5% to 26.6% across configurations, and increased reasoning effort did not substantially reduce these violations.
arXiv:2610.27921v1 Announce Type: new Abstract: A single observation can admit several plausible futures, making uncertainty an essential part of world modelling. However, quantum generative models r...
arXiv:2610.28585v1 Announce Type: cross Abstract: Simulation is a powerful tool for robotics, but building diverse, simulation-ready scenes at scale remains difficult. Reconstructing scenes from sing...
arXiv:2610.28562v1 Announce Type: new Abstract: Many scientific phenomena are best understood as outcomes of underlying optimization problems, yet automated scientific discovery has largely focused o...
arXiv:2610.28578v1 Announce Type: new Abstract: In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adapti...
WaveCommitments is an open‑source framework that enables private and verifiable marketplaces for autonomous speech agents. It combines confidential asset valuation using Data Shapley within a trusted execution environment with multivariate polynomial commitments, allowing selective openings and tamper‑evident provenance. Experiments on three datasets and state‑of‑the‑art encoders, including Whisper, show up to 20× faster benchmarks and 39× smaller proofs, while also revealing how speaker value varies across tasks and encoders.
arXiv:2610.27272v1 Announce Type: cross Abstract: Producing synthetic data for comparison testing a migrated COBOL application is a major challenge that agentic migrations face today. Our prior paper...
The article reviews how large language models (LLMs) enable industrial agents to move beyond predefined workflows toward autonomous planning and execution in smart manufacturing. It identifies five key challenges, defines the concept and core characteristics of industrial agents, and presents a unified taxonomy covering application scenarios, embodiment forms, and capability levels. The authors propose a four‑layer system architecture with core modules for closed‑loop task execution, review representative applications across the industrial lifecycle, and outline future research directions.
SPEM is a lightweight, structure‑aware procedural memory framework designed to improve skill use in large language model agents. It stores individual skills in an Atomic Skill Memory and reusable skill compositions in a Skill‑DAG Memory, reusing high‑confidence templates when possible and falling back to atomic skills with a Skill‑GNN for state‑aware selection. The system writes successful executions back as new Skill‑DAGs, enabling continuous accumulation of procedural knowledge and achieving higher effectiveness‑efficiency trade‑offs on ALFWorld and SkillsBench benchmarks.