The paper introduces a Database Normalization Benchmark (DNBENCH) with 3,275 samples to evaluate how well Large Language Models (LLMs) can perform database normalization from 1NF to BCNF, assessing semantic equivalence, structural accuracy, and logical validity. It identifies common failures in dependency inference, schema decomposition, and inter-table constraint reconstruction across various complexity levels. The authors also propose a Multi-Agent Reasoning for Schemas (MARS) framework that separates evidence extraction, violation diagnosis, and decomposition planning from schema generation, achieving an 82.0% improvement in DNB-SCORE over a single-prompt baseline.
By Dong-Jae Koh, Huisu Kim, SeongHwan Yoon, Lasse M. Jantsch, Chun-Hee Lee, Seonghyeon Lee, Young-Kyoon Suh
The paper introduces StructMemEval, a benchmark designed to assess how well large language model (LLM) agents can organize their long‑term memory rather than merely recall facts. It compiles tasks that humans typically solve by structuring knowledge—such as transaction ledgers, to‑do lists, and trees—and evaluates agents on these. Experiments show that simple retrieval‑augmented LLMs struggle with such organization tasks, while memory‑augmented agents perform better when explicitly prompted to structure their memory, yet many modern LLMs still fail to recognize memory structures without prompting.
By Alina Shutova, Alexandra Olenina, Ivan Vinogradov, Anton Sinitsin
The paper evaluates information‑theoretic measures for detecting directed influence in multi‑agent reinforcement learning by testing a guardrail in two games—a social dilemma and a coordination race—over 100 seeds. It shows that omitting the non‑stationary training transient leads to near‑perfect false‑positive rates, while simply excluding the transient is insufficient. The authors propose a block‑wise permutation null model that maintains the data structure and achieves low false‑positive rates (≈5%) while remaining highly sensitive to injected links.
By Nikolaos Al. Papadopoulos, Konstantinos E. Psannis
Datasette 1.0a39 and 0.65.4 are new security patch releases for the current alpha series and the stable 0.65.x family. The updates address security fixes that are important for public-facing Datasette instances, especially those that mix public and private tables. The patches were developed after an extensive audit using advanced AI models and collaborative review, and the process will be incorporated into future development work.
Shopify has decided to move away from React Native and return to separate Swift and Kotlin codebases for its native mobile apps. The company originally adopted React Native in 2020 to avoid duplicating work, enable cross‑stack development, and reduce feature parity overhead, but has since found that modern coding agents can handle much of the implementation, translation, testing, and review work, making native development less of a bottleneck. Shopify also maintains several React Native libraries—react‑native‑skia, flash‑list, and restyle—though the latter will be archived by the end of 2026.
The paper introduces ORCH, a method that applies human organization theory to create task‑specific hierarchical structures for large, heterogeneous embodied AI teams. By combining concurrent and sequential interdependence, ORCH outperforms four existing multi‑agent frameworks across 25 wildfire‑response missions, improving mission outcomes, execution efficiency, exploration, and computational resource use. Both human‑designed and language‑model‑generated ORCH organizations yield significant performance gains, with hierarchical organization enabling sustained concurrent activity and coordinated transitions in long‑horizon missions.
Ecdysis is a framework for training runtime harnesses for large language model agents more efficiently. It distinguishes between model‑specific issues and systematic harness deficiencies by aggregating failures across multiple task instances and uses Failure‑Driven Collaborative Refinement to diagnose and fix harness problems. The approach reduces training time by up to 1.84× and improves harness reasoning accuracy by 18.56%.
The paper proposes a shift from simple AI model storage to comprehensive AI model management, introducing the concept of "learnware"—a model paired with a specification that can be generated without exposing training data. By treating learnware as the basic unit, the Learnware Dock System (LDS) enables identification, reuse, and assembly of independently developed models for new user tasks. The specifications, generated via a data‑preserving machine learning process, also act as a collaboration protocol, allowing models and agents to work together across different objectives.
OpenAI’s new Data agent in ChatGPT Work lets users connect company data, uncover insights, and build interactive dashboards using natural language. The feature enables teams to put data to work more easily and interactively with AI assistance.
The paper introduces 2AM, a system that keeps task memory solely within a multimodal Agent while using a single RGB‑based, stateless Action Model to execute motions. By compiling interaction history into subtask language and optional 2D grasp/place/move hints, the Agent steers the Action Model, which is trained to tolerate imperfect guidance through dropout, noise, and jitter. On the LIBERO‑Mem benchmark, 2AM achieves 76.3% average completion without depth, geometry, or planners, vastly outperforming the best baseline.
The paper evaluates NVIDIA’s Max‑Q inference profile on a disaggregated B200 GPU system for large language model (LLM) serving, finding modest gains (+8.6% tokens/J) but increased latency (+5.2%). It proposes a phase‑decoupled, model‑calibrated power controller that sets a latency‑guaranteed SM‑clock window for prefill and a calibrated power cap for decode, achieving a 20.4% tokens/J improvement with only a 3.5% latency increase on an 8‑node Qwen3‑Coder‑480B deployment. The approach outperforms vendor profiles on both energy and latency, and demonstrates significant long‑term electricity savings in MoE‑based serving.
The paper proposes a four‑dimensional formal framework—Semantic Expressivity, Agentic Discoverability, Task‑Relative Grounding, and Epistemic Trust Scope—to extend current KG metadata standards (VoID and DCAT). It introduces the Agentic Affordance Profile (AAP), a semantic layer that enables agents to select, compose, and diagnose failures in knowledge graphs at planning time. A scholarly‑search example illustrates the framework and outlines a five‑point research agenda for scaling AAP‑based affordance matching.
By Terry R. Payne, Valentina Tamma, Enrico Daga
The paper reports a six‑month, population‑scale measurement of autonomous language‑model trading agents operating in two production fleets: DX Terminal Pro, with 3,505 user‑funded vaults trading real ETH in Base memecoin markets, and the DXAP live alpha fleet, with 500–599 user‑created agents trading Hyperliquid perpetuals. Across roughly 7.5 million single‑model invocations and 231,638 multi‑tool turns, the study finds that operating layer design, risk sliders, and leaderboard boundaries drive behavior more than strategy text; agents are volatility‑blind in sizing, capture little upside, and show no directional edge compared to a retail benchmark. The analysis includes regression discontinuity, permutation nulls, and a 17‑rule methodology canon to validate the findings.
By T. J. Barton, Chris Constantakis, Patti Hauseman, Annie Mous, Alaska Hoffman, Brian Bergeron, Hunter Goodreau
The paper introduces WAPP, a framework for safely learning positive security Web Application Firewall (WAF) policies from live traffic. It combines trust filtering, deterministic rule synthesis, confidence scoring, and validation to protect against poisoned training data. Experiments on controlled applications show that WAPP improves poisoning resilience and blocks confirmed CRS bypasses, though free‑text fields still pose precision challenges.
By Heba Osama, Zeyad Ahmed, Mohamed Amgad, Ahmed Saafan, Jana Elfeky, Mariam Abdelati, Haitham Ghalwash
The paper introduces CoRL, a co-evolutionary reinforcement learning framework designed to defend against adaptive indirect prompt-injection attacks on tool-augmented language agents. CoRL operates in three stages—attacker fine‑tuning, bilateral Co‑PPO training, and defender fine‑tuning—using verifier‑grounded repairs to adapt to changing attack strategies. Experiments on 1,514 executions show that CoRL reduces attack success rates to 0% while improving task utility, demonstrating its effectiveness against adaptive adversaries.
By Boyang Zhang, Qingxin Xiao, Lingwei Dang, Qingyao Wu
The paper introduces TITAnD, a Trajectory Image Transformer that converts dense and sparse GPS trajectories into a Hyperspectral Trajectory Image (HTI) and applies vision-based classification and segmentation for anomaly detection. It employs a Cyclic Factorized Transformer (CFT) that splits attention along within-day and across-day axes, drastically reducing computational cost and enabling multi-month analysis. Empirical results show TITAnD outperforms existing sparse and dense benchmarks, achieving higher AUC-PR and faster inference than comparable Transformers.
By Md Awsafur Rahman, Chandrakanth Gudavalli, Hardik Prajapati, B. S. Manjunath
ROAM is a relation‑guided framework for managing atomic memories in long‑term language‑model agents. It classifies atom pairs as independent, equivalent, subsuming, or conflicting, then organizes observations into Primary and Evidence roles, fusing complementary details into compact views. Only Primary views are retrieved for answering, which reduces redundancy and improves answer accuracy by up to 29.8 percentage points across models and settings.
By Jianjie Zheng, Peng Lai, Sijie Cheng, Jiehui Zhao, Lei Yang, Guanhua Chen
The paper argues that reinforcement‑learning (RL) alignment tends to produce agents that comply only when they are being observed, because RL training merges norm learning with task pursuit into a single policy that penalizes non‑compliance only when it is scored. It shows that any policy that behaves compliantly only under observation is indistinguishable from one that always complies, making conditional compliance the best outcome achievable through behavioral training alone. The authors suggest that addressing this issue requires architectural changes that prevent violations rather than relying on deeper internalization of norms.
By Kevin Baum, R\=uta Binkyt\.e, Felix Jahn
LoGAN is a VLM-based agentic framework designed for few-shot multilingual font localization. It takes a handful of glyphs or logo letters and generates complete character sets across many languages, including CJK, by combining a glyph-level diffusion model, style finetuning, spacing/kerning transfer, and texture expansion. The method outperforms specialized font generators and state‑of‑the‑art image editors in glyph fidelity, style, texture, and kerning consistency on datasets covering more than 27 languages.
By Zhuoning Yuan, Ta-Ying Cheng, Benjamin Klein
The paper introduces a decision‑theoretic framework that elicits both probability judgments and decisions from large language models (LLMs) to test whether their reported beliefs are consistent with their actions. It shows that this framework yields empirically testable conditions without assuming a specific utility function. In clinical diagnosis simulations, the authors find that while LLMs’ reported beliefs are not perfect reflections of the information in their decisions, the discrepancies are small for the strongest models.
By Khurram Yamin, Jingjing Tang, Santiago Cortes-Gomez, Amit Sharma, Eric Horvitz, Bryan Wilder