Record 01092026 · captured 2026-09-02
The world looked up Toxic (2026 film). 30 tracked subjects, 25 discussions, 25 papers. This record is frozen and will not change.
Complete record JSON
What the most people looked up, ranked by Wikipedia pageviews for that day.
Toxic: A Fairy Tale for Grown-Ups is a 2026 Indian psychological thriller gangster film directed by Geetu Mohandas and jointly produced by Venkat K. Narayana and Yash through KVN Productions and Monster Mind Creations respectively. It stars Yash in the lead ro
Dolly Rebecca Parton Dean was an American singer-songwriter, actress and businesswoman. Dubbed the "Queen of Country", Parton was one of the most successful country music performers in history. She was also known for her cultural influence and philanthropy via
Killing of the Clancy children
On January 24, 2023, Lindsay Clancy allegedly strangled her three children, five-year-old Cora, three-year-old Dawson, and eight-month-old Callan, at the family's home in Duxbury, Massachusetts, United States. She then attempted suicide by cutting her wrists a
.xyz is a top-level domain name that was proposed in ICANN's new generic top-level domain (gTLD) Program for consisting of the last three letters of the Latin-script alphabet. XYZ.com and CentralNic are the registries for the domain, which was created by entre
The following notable deaths occurred in 2026. Names are reported under the date of death, in alphabetical order. A typical entry reports information in the following sequence:Name, age, country of citizenship at birth, subsequent nationality, what subject was
The Whisper Man is a 2026 American crime thriller film directed by James Ashcroft and written by Ben Jacoby and Chase Palmer. It is based on the novel of the same name by Alex North and stars Robert De Niro, Michelle Monaghan, and Adam Scott.
Spider-Man: Brand New Day is a 2026 American superhero film based on the Marvel Comics character Spider-Man. Produced by Columbia Pictures, Marvel Studios, and Pascal Pictures, and distributed by Sony Pictures Releasing, it is the 38th film in the Marvel Cinem
Lanterns is an American superhero television series created by Chris Mundy, Damon Lindelof, and Tom King for HBO, based on the DC Comics Green Lantern characters Hal Jordan and John Stewart. It is the third television series in the DC Universe (DCU). It featur
Coyote vs. Acme is a 2026 American live-action animated legal comedy film directed by Dave Green and written by Samy Burch, who developed the story with James Gunn and Jeremy Slater. Based on the 1990 The New Yorker magazine article "Coyote v. Acme" by Ian Fra
Lake Ontario is one of the five Great Lakes of North America. It is bounded on the north, west, and southwest by the Canadian province of Ontario, and on the south and east by the U.S. state of New York. The Canada–United States border spans the centre of the
The Odyssey is a 2026 epic action fantasy film written and directed by Christopher Nolan, who produced it with his wife Emma Thomas. An adaptation of Homer's ancient Greek epic poem the Odyssey, it stars an ensemble cast including Matt Damon, Tom Holland, Anne
On the morning of 26 August 2026, a series of flash floods completely destroyed the Gyirong checkpoint on the China–Nepal border and struck dozens of settlements along a 72 km (45 mi) stretch of the Trishuli River in Nepal.
Timothy James Curry was an English actor and singer who amassed more than 240 credits on screen and stage in a career which spanned nearly 60 years. Curry made his acting debut in the West End production of Hair (1968–1969) and gained wide recognition for port
Hanuman Ansh is a 2026 Hindi-language devotional drama film, written and directed by Vishal Chaturvedi. Based on the life of Neem Karoli Baba, popularly known as Maharaj-ji. Hanuman Ansh is produced by Swambhu Media Network Pvt. Ltd., Ragini S., Namrata G. S.,
Neatsville is an unincorporated community in Adair County, in the U.S. state of Kentucky. It is located at the junction of Kentucky Route 206 and Kentucky Route 76. Its elevation is 705 feet (215 m). For unknown reasons, the town's name was spelled as Neetsvil
List of highest-grossing films
Films generate income from several revenue streams, including theatrical exhibition, home video, television broadcast rights, and merchandising. However, theatrical box-office earnings are the primary metric for trade publications in assessing the success of a
Aaron Charles Donald is an American professional football defensive tackle for the Los Angeles Rams of the National Football League (NFL). He is considered the greatest defensive player of all time.
Lionel Andrés "Leo" Messi is an Argentine professional footballer who plays as a forward for and captains Major League Soccer (MLS) club Inter Miami. Widely regarded as one of the greatest players in history, Messi has set numerous records for individual accol
Buddy is a 2026 American black comedy supernatural horror film directed by Casper Kelly and written by Kelly and Jamie King. The film stars Cristin Milioti, Delaney Quinn, Patton Oswalt, Michael Shannon, Topher Grace, and Keegan-Michael Key as the voice of the
Anna's Archive is an open source search engine for shadow libraries that was launched by the pseudonymous Anna shortly after law enforcement efforts to shut down Z-Library in 2022. The site aggregates records from Z-Library, Sci-Hub, and Library Genesis (LibGe
The 2026 All In, also promoted as All In: London, was a professional wrestling pay-per-view (PPV) event produced by the American company All Elite Wrestling (AEW). It was AEW's fourth annual All In, and the fifth overall. The event took place on August 30, 202
John Charles Galliano is a British fashion designer. He was the creative director of his eponymous label John Galliano and French fashion houses Givenchy and Dior. From 2014 to 2024, Galliano was the creative director of Paris-based fashion house Maison Margie
Novak Djokovic is a Serbian professional tennis player. He has been ranked as the world No. 1 in men's singles by the Association of Tennis Professionals (ATP) for a record 428 weeks, finished as the year-end No. 1 a record eight times, and has been ranked No.
9 to 5 is a 1980 American comedy film directed by Colin Higgins, who wrote the screenplay with Patricia Resnick, and starring Jane Fonda, Lily Tomlin, Dolly Parton in her film debut, Dabney Coleman, Elizabeth Wilson, and Sterling Hayden. It tells the story of
Mariano Navone is an Argentine professional tennis player. He has a career-high ATP singles ranking of world No. 29 achieved on 10 June 2024 and a doubles ranking of No. 140, reached on 16 June 2025. He is currently the No. 3 singles player from Argentina.
Bradley Jean-Manuel Essolisam Addo Barcola is a French professional footballer who plays as a forward for Premier League club Liverpool and the France national team. Regarded as one of the best wingers in the world, he is known for his speed, agility and dribb
Bethlehem Kudumba Unit is a 2026 Indian Malayalam-language romantic comedy film starring Nivin Pauly and Mamitha Baiju in the lead roles, directed by Girish A. D. and produced by Bhavana Studios, Fahadh Faasil, Dileesh Pothan and Syam Pushkaran.
The Dog Stars is a 2026 post-apocalyptic action thriller film directed and produced by Ridley Scott, from a screenplay by Mark L. Smith, based on the 2012 novel by Peter Heller. The film stars Jacob Elordi, Josh Brolin, Margaret Qualley, and Guy Pearce, and fo
Harald V was the King of Norway from 1991 until his death in 2026.
Limonene is a slightly yellow-green liquid aliphatic hydrocarbon classified as a cyclic monoterpene, and is the major component in the fragrance and essential oil of citrus fruit peels, taking its name from Italian limone ("lemon").
What the people building things argued about, from Hacker News.
Papers submitted to arXiv cs.AI that day.
Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation
Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing efficient evaluation methods select representative subsets to estimate full-benchmark performance, but are largely result-only: they fit historical pass/fail response matrices or static task semantics, discarding how agents solve problems. We pro
Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation
The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-world repositories often exceed the input length limits of LLMs, existing approaches commonly adopt retrieval-augmented generation (RAG) to provide repository-specific context. Despite improving repository-context retrieval, existing methods ty
CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?
Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a local plugin change can propagate through dependencies and cleanup. We introduce CordisBench, a 1,200-question benchmark of this lifecycle reasoning. It combines a controlled formal setting with programs executed against Cordis, a runtime that manages component dependencie
The Rise of Verbal Reinforcement Learning
Natural language is emerging as a primary feedback channel for improving language agents, capable of conveying intent, preferences, and causal structure in forms interpretable by both humans and modern language models. We call this paradigm Verbal Reinforcement Learning (VRL) and offer the first unified account of it. We organize the field around a single axis, \textit{when} verbal feedback takes effect in an agent's
Mechanism Design for Alignment and Control
We develop a framework for mechanism design with AI agents whose alignment (preferences) and capabilities (feasible actions and information) are unknown. We want such agents to act on our behalf so mechanisms must incentivize both honesty and obedience. A one-sided imitation structure---capabilities can be concealed but not counterfeited---yields a revelation principle, a characterization of implementable policies vi
Designing Proactive Thought Partners for Writing
Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promises to provide the right support at the right time, yet existing proactive tools largely focus on generic textual assistance, such as autocomplete. This paper studies the design space of proactive thought partners: AI agents that proactively offer customizable, higher-lev
Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs
How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during LLM post-training remains an open problem. Existing work characterizes only broad trends (e.g., SFT dominates in low-data regimes), lacks a principled allocation framework, and does not examine whether the optimal ratio transfers across model sizes. We frame this problem in terms of near-optimality: rat
Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers
Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they must be queried at every step, do not improve from environment interaction, and can repeat systematic errors. We study how to learn a cheap autonomous policy from an online, expensive, and imperfect but informative VLM teacher. We propose SAGE (Selective Agent Guidanc
From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification
Large language models (LLMs) struggle to classify text into taxonomies with many semantically similar labels, as the distinctions are domain-specific and not captured by pre-training. To handle large label spaces, a common approach retrieves top-$K$ candidate labels by embedding similarity and prompt the LLM to choose among them. However, top-$K$ retrieval reduces the number of candidates but does not help the model
H3-World: Turning Language Understanding into World Control
We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model. Our key finding is that, as large video generators become more capable, language is emerging as a natural interface for control. MiniMax-H3, for example, already supports zero-shot control of character behavior and camera motion through natural-language instructions. Building on this, H3-World tu
We evaluate embedding retrieval where surface form and meaning are pulled apart on purpose: retrieving items that share underlying structure but not wording, in two unrelated domains under one protocol, competition mathematics (MathNet-Retrieve; 500 queries, 117,088-item corpus) and embodied-agent trajectories (ALFWorld-derived; 118 queries, 336 trajectories). In mathematics the failure is complete: strict Hit@1 at t
Automated lesion segmentation in whole-body PET/CT is complicated by the variety of physiological tracer uptake patterns and by the differing appearance of lesions across tracers. The autoPET/CT V challenge addresses this by making segmentation interactive: user scribbles marking foreground and background are supplied alongside the image, and the algorithm is expected to exploit them. We present our submission, a scr
Can LLMs Discover Scientific Laws in Real and Parallel Worlds?
Scientific equation discovery has long been central to scientific progress, proceeding through iterative cycles of hypothesis generation, observational testing, and refinement under scientific constraints. As LLM capabilities advance and their role in AI for Science expands, it remains an open problem whether they can genuinely discover scientific laws and how this ability should be evaluated. Existing evaluations, h
A Mathematical Theory of Reusable Neural Bases for Network Compression
As large AI models become increasingly prevalent across a wide range of applications, memory cost has become a critical bottleneck in both training and inference. To mitigate this issue, we introduce the Linear Reusable Neural Bases Architecture (LRNBA), a novel framework aimed at improving parameter efficiency and reducing memory cost. Inspired by recurrent neural network (RNN) designs, the core idea of our approach
Can LLMs Design Video Coding Tools? A Case Study on Planar Mode
This paper explores whether large language models (LLMs) can design video coding tools, a highly challenging task due to the intricate algorithmic coupling of tool modifications. In particular, we present an empirical case study on the Planar mode, a long-standing intra prediction tool in video coding standards. Our experiments operate within a generation-and-evaluation loop, with the LLM generating new Planar predic
EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
Scientific agents must learn not only how to reason, but also what to believe. However, existing LLM agents typically express scientific hypotheses in free-form text, leaving their beliefs implicit and difficult to test or revise. We introduce EvoSCM, which equips scientific agents with explicit structural causal models that evolve as new experimental evidence is collected. EvoSCM maintains a population of competing
A durable assumption holds that graph analytics requires a purpose-built graph engine, and that relational systems are ill-suited to connected data. We argue the opposite for the workloads enterprises actually run. A columnar relational engine fronted by a graph query language matches or exceeds native graph engines on analytical graph queries, and - decisively - scales past the point where in-memory graph engines fa
When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation
Interactive simulations increasingly evaluate policies in markets populated by language-model agents. Their outputs can look economic---prices, profits, consumer surplus, and welfare---without instantiating the behavior named in the claim. We audit this risk in a multi-turn buyer--seller testbed for configurable hotel transactions. An initial implementation reported welfare gains from two marketplace guardrails of +8
TempCloze: Can Video-LLMs Identify the Missing Middle?
Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors. To reduce such shortcuts, we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs. Given the beginning and ending clips of a video, models must identify the true missing middle from four candidate
LatentPress: Context Compression Beyond Text and Vision
Compressed context is usually carried as human-readable text or as rendered images that must be decoded, even when its consumer is a language model. We introduce LatentPress, which writes conversational histories and long documents into a third representation: continuous memory tokens that a frozen decoder reads directly through its input-embedding interface, with no text reconstruction at inference. A small reader-m
Optimizing Byzantine Node Placement in Decentralized Federated Learning
Security evaluations of decentralized federated learning (DFL) typically focus on how Byzantine participants behave, while largely overlooking which participants are compromised. Yet, because aggregation is distributed over a communication graph, the placement of Byzantine nodes determines how malicious influence propagates through the network. We therefore treat Byzantine placement as an explicit adversarial decisio
Rethinking Learnability in Offline Data-driven Optimization
Black-Box Optimization (BBO) has found broad applications, but evolutionary algorithms and Bayesian optimization face efficiency challenges as real-world BBO problems grow increasingly complex. Data-driven optimization improves the efficiency of BBO algorithms by learning from data. Offline data-driven optimization seeks high-quality solutions using only a fixed set of previous evaluations, attracting substantial att
GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions
The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implications for safety and monitorability as well as for linguistic accounts of LLMs. To address these questions, we introduce GlossoGen, a novel platform for studying multi-agent language evolution in complex scenarios. Within GlossoGen, we build the SaveVeyru scenario, whic
Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls f
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executio
Origins publishing files written for machines rather than people. Measured against a frozen cohort, so a change in the number means a change in adoption.
| Signal | Web head Tranco top 1,000 n=1,000 | Web tail sampled to rank 100k n=1,000 | AI-native model & dev platforms n=110 |
|---|---|---|---|
| Any agent-facing signal | 10.9% (109) | 2.9% (29) | 74.55% (82) |
| llms.txt (apex domain) | 8.8% (88) | 2.4% (24) | 57.27% (63) |
| llms.txt (docs subdomain) | 3.5% (35) | 0.7% (7) | 44.55% (49) |
| .well-known/mcp.json | 0.6% (6) | 0.1% (1) | 7.27% (8) |
| .well-known/agents.txt | 0.3% (3) | 0.1% (1) | 0% (0) |
| ai.txt | 0.2% (2) | 0.1% (1) | 0% (0) |
| ai-plugin.json (deprecated) | 0.6% (6) | 0.1% (1) | 0.91% (1) |
Notable events recorded on this day and month across all years.