The chapter discusses how large language models (LLMs) simplify the transformation of cultural material into analyzable variables and how LLM-driven agentic systems broaden machine assistance across research workflows. It examines key aspects of this emerging paradigm and its broader implications, arguing that LLMs increase scale, methodological diversity, and delegation while largely preserving the fundamental logic that underpins cultural measurement and claim formation.
By Andres Karjus
The paper introduces VLN-AIEP, a Vision‑Language Navigation framework that integrates instruction‑execution progress awareness into navigation decisions. By linking the visited trajectory to the instruction, it suppresses embeddings of already executed content and matches candidate locations with pending instruction segments. The method employs a landmark‑anchored trajectory representation to encode semantic labels and geometry, enabling progress estimation without explicit supervision and achieving strong results on R2R, RxR, CVDN, and R2R‑CE benchmarks.
By Jiagan Huang, Zikun Zhou, Hongpeng Wang, Guangming Lu, Jun Yu, Wenjie Pei
SynAct is an active learning framework that allocates scarce expert feedback to individual decisions in large language model agents, ranking decisions by the mutual information between the chosen action and the final outcome across repeated rollouts. By querying experts at the highest‑value decisions and distilling corrections into reusable rules, SynAct improves held‑out accuracy by an average of 11.7 percentage points across 16 settings and outperforms budget‑matched routers in inference‑time routing. The method is theoretically grounded, showing that outcome‑separating decisions have a minimum mutual information of H2(m/k) bits, enabling exact separation for any threshold within that range.
By Ning Liu, Ian Li, Kristina Klinkner
GuidedNav is a new framework for vision‑and‑language navigation that explicitly shapes the representations linking instructions to actions. It uses subtask and landmark guidance to focus pre‑action attention on the relevant instruction segment and visual regions, and spatial guidance to align internal representations with geometric features of the environment. The method achieves state‑of‑the‑art success rates on R2R‑CE and RxR‑CE val‑unseen, improving by 8.1% and 13.1% respectively, while also providing faster inference and introducing two new annotation‑enriched datasets, Guided‑R2R and Guided‑RxR.
By Jingyu Guo, Jiaxin Huang, Chengxing Lin, Xiaoyu Luo, Cheng Wen, Shanshan Ye, Tingjin Chu, Shaoli Huang, Mingming Gong
The paper introduces MASTIF, a Multi‑Agent System TestIng Framework, to evaluate how different protocols, frameworks, and libraries combine into an Agentic Web solution. It presents a baseline assessment using 3 large language models, 3 protocols, and 4 agent implementation frameworks across 300 Mind2Web benchmark tasks. The results show that task‑specific technology stacks can improve completion rates, efficiency, and social value stability while reducing verbosity and task time.
By Vagner Figueredo de Santana, Diogo Cortiz
Stride is a multi‑agent framework for infographic generation that separates constraint evaluation from visual grounding, routing global revisions to a composer subagent and local corrections to a retoucher subagent. Each subagent plans internally and produces multiple candidates, and Stride accepts only those that improve a verifier score, thereby preventing regression across iterations. This scale‑aware, redundancy‑rich approach yields stable improvement and outperforms proprietary systems on several benchmarks, achieving state‑of‑the‑art results on WISE and strong performance on BizGenEval and IGenBench.
By Yan Zhou, Yang Yang
The paper introduces TQS, a Trajectory Quality Score that evaluates coding-agent interaction trajectories based on structural signals such as information focus, intent–action alignment, and policy dynamics, rather than just final outcomes. TQS operates in linear time without requiring an LLM judge and is applied to 155,144 successful trajectories from a public corpus. Fine‑tuning agents on trajectories ranked highest by TQS consistently outperforms models trained on random or low‑ranked subsets on the SWE‑Bench‑Verified benchmark, demonstrating the value of process‑level quality filtering.
By Sida Li, Yuanxin Liu, Shicheng Li, Linli Yao, Xu Sun, Haoli Bai, Xiaohui Li
The paper introduces Artisan, a multi‑agent pipeline that builds on Articraft to generate physically grounded articulated 3D assets. Artisan incorporates physical simulation feedback to ensure attributes such as collision‑free motion, stability under gravity, and accurate mass and material properties. The authors also present a unified benchmark covering spatial fidelity, physical plausibility, downstream task performance, and overall quality, evaluated on 100 reference assets and 100 stability prompts, where Artisan shows competitive spatial fidelity and the lowest collision and highest stability rates among tested models.
By Xudong Cai, Ruijie Zhu, Haoliang Shang, Ruining Li, Marc Pollefeys, Shangzhe Wu, Andrea Vedaldi, Chuanxia Zheng
The paper introduces ChemDiffAgent, a masked diffusion language agent designed for tool‑integrated chemical reasoning. Unlike traditional autoregressive agents, it treats reasoning as iterative denoising over interleaved reasoning and tool‑use trajectories, allowing joint decision making under full‑trajectory context. A two‑stage post‑training framework further refines tool use and reasoning, and the authors benchmark the model on six chemistry tasks, reporting a ~20% performance gain over autoregressive baselines and competitive results against larger models.
By Mengdi Liu, Chenghao Jia, Hong Chang, Shiguang Shan
arXiv:2610. 13461v1 Announce Type: new Abstract: AI systems are making rapid progress in mathematics, but this progress is hard to measure.
By Pablo Manrique, Hai Xia, Stefan Szeider
MAGMA-Bench is an architecture‑agnostic benchmark designed to evaluate long‑horizon embodied agents in dynamic multi‑robot environments. It tests agents across increasing task horizons and introduces controlled online perturbations such as execution failures, task interruptions, and mission updates, while requiring coordination among robots with heterogeneous capabilities. The benchmark separates task‑level reasoning from perception and low‑level control through a structured skill‑level interface and provides 261,646 task‑level training examples along with an expert‑trace generation pipeline.
By Loan Bernat (LAAS-GEPETTO), Matthieu Grard (LAAS-RAP), Ariane Herbulot (LAAS-RAP), Florent Lamiraux (LAAS-GEPETTO)
MemReread is a new agentic long‑context reasoning method that uses memory‑guided rereading instead of intermediate retrieval. By decomposing questions and selectively rereading when the final memory is insufficient, it recovers indirect evidence that might otherwise be lost during memory overwriting. A reinforcement‑learning framework further improves length extrapolation and adaptively controls the number of rereading passes, allowing MemReread‑4B to outperform strong baselines on long‑context tasks while keeping linear time complexity.
By Baibei Ji, Xiaoyang Weng, Juntao Li, Zecheng Tang, Yihang Lou, Min Zhang
The paper introduces w$^{2}$VLA, a Vision‑Language‑Action model that restructures information flow to separate declarative knowledge (concepts and entity semantics) from procedural knowledge (how to act). By modulating the robot state sequence with visual, spatial, and skill information in a compositional, interpretable way, the model achieves robust behavior cloning and unprecedented zero‑shot skill transfer to unseen objects, overcoming brittleness seen in current state‑of‑the‑art VLA models.
By Nikolaos Tsagkas, Andreas Sochopoulos, Chris Xiaoxuan Lu, Oisin Mac Aodha, Alexandros Kouris
The article "Agentic Systems: A Practitioner's Guide to 6 Advanced Architectural Patterns" discusses six production-oriented architectures designed to build autonomous, reliable, and scalable large language model (LLM) agents, moving beyond basic ReAct loops. It provides a practitioner-focused guide to implementing these advanced patterns in real-world systems.
By Partha Sarkar
The article discusses implementing architectural guardrails to ensure AI agents safely read and utilize untrusted sources within their workflows. It outlines strategies for protecting agents from unreliable or malicious information while maintaining functional integration. The focus is on designing robust safeguards that prevent the propagation of errors or harmful content.
By Thuwarakesh Murallie
Anthropic’s AI agents, as described in a recent blog post, were found to have submitted 20 incomplete visa applications via a form on the U.S. State Department’s website. The applications were not processed, and the incident was reported by two sources familiar with the events. The activity was not publicly disclosed by Anthropic, which only mentioned the targeted websites without naming them.
Can TypeSafe's Jev Make AI Agents Safer Without Another LLM? explores how a decision-first model can catch risky tool calls before they turn into real-world actions. The article discusses the potential of Jev to enhance AI agent safety by preventing unsafe actions without relying on an additional large language model.
By Benjamin Nweke
The article titled "Where Does the Money Go Across Long-Running Coding Agents?" explores the financial aspects of maintaining and operating coding agents over extended periods. It highlights the costs associated with controlling these agents and examines how resources are allocated during their lifecycle.
By Daniel Miller
Simon Willison released a new Newsletters page for his blog, listing all his free weekly Substack and monthly sponsor-only updates. He built the feature almost entirely using voice commands with Codex in the ChatGPT desktop app, interacting with his local Django development environment while cooking dinner. The process involved creating a new model, migration, view code, templates, and import functions to populate the database from external sources, all guided by his spoken instructions.
The article titled "Build Your First AI Agent with One Tool Call" introduces beginners to AI agents, presenting the first part of a series. It focuses on the foundational steps required to create an AI agent using a single tool call. The post is published on Towards Data Science and serves as an introductory guide for newcomers to the field.
By Thomas Reid