arXiv:2609.02981v1 Announce Type: new Abstract: Artificial intelligence is changing the form of applied English materials from fixed paper sequences to adaptive learning systems that can diagnose learners, recommend tasks, and provide formative feedback. This paper studies the structure and application of a new practical English textbook driven by artificial intelligence. A five-layer architecture is proposed: knowle
arXiv:2609.03209v1 Announce Type: new Abstract: We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic policy selects and runs a pre-approved analytical program that returns both results and evidence. We show that this restriction can remain expressive within a defined analytical class, using relational operations plus aggregation, comparison, windows, rank
arXiv:2609.03236v1 Announce Type: new Abstract: Tool-using LLM agents spend wall-clock time not only on model inference but also in serial action--observation turns, where each tool call, environment transition, and observation can delay subsequent decisions. We introduce \textbf{Speculative Macro Commit} (SMC), a runtime mechanism for a two-tier agent system: a large authoritative actor model produces the official t
arXiv:2609.03340v1 Announce Type: new Abstract: Distributed LLM-agent teams can read the latest shared facts and still act on an obsolete plan. A planner may derive an action from requirement $r_3$, another agent may commit $r_4$, and an executor may receive $r_4$ without replacing the plan derived from $r_3$. We call this \emph{stale-plan execution}: state freshness does not establish that the plan authorizing an ac
arXiv:2609.03402v1 Announce Type: new Abstract: Artificial intelligence (AI) teaching assistants powered by large language models (LLMs) offer scalable educational support but often provide limited personalization. This study presents a prompt-engineering-based framework for personalizing general-purpose LLM/RAG-based AI teaching assistants such as Jill Watson across academic disciplines and courses. The framework ad
arXiv:2609.03407v1 Announce Type: new Abstract: People increasingly turn to large language models (LLMs) for everyday advice, making ethically charged interpersonal problems a practical moral-advisory context. Most prior work has studied this context through single-turn judgments or pressure-laden rebuttals, assumptions that poorly match how guidance is sought in real-world contexts. These assumptions leave unclear w
arXiv:2609.03416v1 Announce Type: new Abstract: LLM-empowered paper-code discrepancy detection has received growing concern since the scaling of research submissions exceeds the manual review capability. However, the limited context capacity and one-sided discrepancy detection of existing single-agent LLM paradigms lead to an inferior recall performance in detecting discrepancies. In this paper, we propose Dude, the
arXiv:2609.03423v1 Announce Type: new Abstract: Full-duplex voice agents must continuously decide when to listen, backchannel, interrupt, handle speech overlaps, take the floor, and yield. Existing benchmarks largely test these behaviors through explicit turn-management instructions, while deployed agents are often configured through roles or personas from which the appropriate conversational behavior must be inferre
arXiv:2609.03438v1 Announce Type: new Abstract: Graphical user interface (GUI) agents are increasingly used to execute natural-language instructions on user interfaces, yet real users may issue infeasible instructions due to benign mistakes. A reliable agent should not only know how to act, but also when not to act. In this work, we introduce CONFLICTGUI, a benchmark covering instruction-internal conflicts and instru
arXiv:2609.03460v1 Announce Type: new Abstract: As generative AI makes polished prose cheap to produce, users can no longer rely on fluency as a proxy for truth. We call this failure mode the Fluency Trap: users trust fluent hallucinations while also discounting accurate content once it is disclosed as AI-generated. Binary ``Made with AI'' labels respond with authorship disclosure, but they do not show what supports
arXiv:2609.03478v1 Announce Type: new Abstract: We report on our ongoing project to develop a computational pipeline, AutoGraphForge, for an automated graph-theoretic conjecturing-refuting-formalizing-proving system. Conjecture generation is counterexample-guided and runs in rounds: a Graffiti3 generator proposes conjectures over a small, evolving snapshot table $T$ (initially a few hundred graphs with their computed
arXiv:2609.03493v1 Announce Type: new Abstract: Modern vision-language models (VLMs) can directly answer many image-grounded questions, yet they often struggle with complex queries requiring fine-grained visual details or external knowledge. To acquire this missing evidence, agentic VLMs invoke tools such as image cropping, image search, and text search. However, existing training paradigms primarily evaluate tool-us
The fire department at NASA’s Ames Research Center in California’s Silicon Valley will perform training on the Moffett Federal Airfield beginning Tuesday, Sept. 8 through Friday, Sept. 11. The training will involve the use of a propane-fueled aircraft fire simulator and be conducted from 8 a.m. to 8 p.m. PDT. Because the aircraft simulator is…
Enterprise work spans messages, decisions, projects, and obligations that change over time. An AI agent that starts without this context must reconstruct it...
NASA will host a virtual webinar at 2 p.m. EDT on Friday, Oct. 2, titled “The RS-25 Engine and the Future of Artemis Missions: An Accessible Webinar for the Blind and Low-Vision Community.” This webinar is open to the public, however it is tailored specifically for a blind and low-vision audience. The webinar will last about two hours and…
Running reasoning and agentic AI at the edge has been harder than it needs to be. Until recently, models capable of multi-step reasoning were too large to run...
On Wednesday, June 17, skywatchers across the United States,and parts of Canada,enjoyed a rare event: a daytime lunar occultation of Venus. A lunar occultation occurs when the Moon moves directly in front of another celestial object from our viewpoint on Earth, briefly hiding it from sight. This time, the Moon slipped in front of Venus…
Below you’ll find a general update from the OpCo that covers everything we and the OAT have been working on throughout August. Going forward, we’ll be posting the monthly OpCo updates from this account, as opposed to having an OAT member publish them. Oversight and Transparency Committee (OAT) Second Term Elections The elections for the second term of the OAT were concluded with A.J. Warner and Patrick McCorry being
Executive summary August 2026 counted three governance actions, down from five in July, so the monthly participation threshold dropped back to ≥ 50% (≥ 2/3 votes). Two were on-chain constitutional votes on the Core governor; one was an off-chain Snapshot decision. All three used the 2Q2026 budget schedule with no exceptions. Unlike July, no proposal carried legacy rates. Across three proposals, 32 enrolled delegates
APOD Science APOD APOD: 2026 September 4 – Na… Today’s APOD Archive Submissions Index Search Calendar RSS Education About Discuss APOD Astronomy Picture of the Day Discover the cosmos! Each day a different image or photograph of our fascinating universe is featured, along with a brief explanation written by a professional astronomer. Nā ʻUhane…
Modern AI platforms are no longer a single application behind one login screen. A user may start in a central portal, open a governed dataset, launch a notebook...
NASA will provide live coverage of the launch and docking of a Roscosmos cargo spacecraft carrying about three tons of food, fuel, and supplies for the crew aboard the International Space Station. The unpiloted Progress 96 resupply spacecraft is scheduled to launch at 12:15 p.m. EDT (9:15 p.m. Baikonur time), Wednesday, Sept. 9, on a…
AI agents are learning to do more by working together. A lead agent can break a complex task into smaller jobs and assign those jobs to specialized subagents....
Written by Michelle Minitti, MAHLI Deputy Principal Investigator Earth planning date: Friday, Aug. 21, 2026 After Curiosity’s 14 years on the surface, Mars continues to surprise. Both of our workspaces this week contained features unlike quite anything we have seen in the past , broad, shallow pits (like the one in the image above) dotted…
Now on a three-month, million-mile journey to its final orbit, NASA’s Nancy Grace Roman Space Telescope will soon reveal the universe’s darkest secrets. The mission launched at 7:26 a.m. EDT on Aug. 30 aboard a SpaceX Falcon Heavy rocket from Launch Complex 39A at the agency’s Kennedy Space Center in Florida. Roman pairs a large…
Abstract The following cases from the Watchdog Program have been deemed to constitute high-severity misuse. Accordingly, the Watchdog Committee is proposing to ban three projects identified from these high-severity cases from the ArbitrumDAO: Good Entry Limitless APX Finance (formerly ApolloX) Rationale To strengthen oversight of grant allocations by the DAO and reduce misuse, the ArbitrumDAO approved the Watchdog Pr
OpenAI introduces Daybreak for Frontline Defenders. A $1 billion commitment expands access to frontier cyber AI, training, and support for essential services.
Using GPT-6 Astra, Playco built three themed game prototypes from one grey box foundation and reported 50% fewer manual fixes than with the previous model.
Legora used GPT-6 Astra to review 41 documents in minutes, find all four planted errors, and improve performance by nearly 40% in this financial-review workflow.
Introducing GPT-6 Astra, our most intelligent and aligned model yet, with state-of-the-art capabilities across computer use, coding, cybersecurity, and science.
The new approach has been outlined in a paper led by DPhil student Desiree Cho, with Professor Nigel Shadbolt, Senior Researcher Jun Zhao, and DPhil student Hunar Batra.
Something I keep noticing in treasury discussions across DAOs: runway gets quoted as treasury divided by monthly burn, with the native token counted at spot price. That number is almost always wrong, and wrong in the same direction. If a large share of the treasury is the DAO’s own token, selling a position that size moves the price against you the whole way down. The runway you can actually finance is the one where
Official sources can report their own claims. The Expectancy treats those claims as evidence of what the source said, not independent proof that the claim is true.
