Knowledge catalogue
arXiv:2609.19180v1 Announce Type: new Abstract: Language models face unique challenges in analyzing interdisciplinary scientific research literature. In biophysics research, faithful answers require g
Build your own harness, folks. This is absolute banger paper from NVIDIA on self-evolving agent harnesses. (bookmark it) They introduce SoL-Pi which cuts token traffic by nearly half. And it matches i
arXiv:2509.09121v2 Announce Type: replace Abstract: Large language models (LLMs) excel in general-domain applications, yet their performance often degrades in specialized tasks requiring domain-specif
arXiv:2609.19607v1 Announce Type: cross Abstract: Coding-agent benchmarks are built for broad and comprehensive comparisons, not frequent development decisions. Individual runs vary, full suites are e
arXiv:2609.20005v1 Announce Type: new Abstract: People increasingly turn to AI chatbots for news and explanations of world events. But do they receive the same political answers when they ask in diffe
Grok Bot summary of SpaceX CFO Bret Johnsen’s new interview with Tony Kim at SpaceX Mission Control. Bret’s path - Came from semiconductors (Qualcomm, Broadcom; was CFO of MindSpeed) - Barely knew Spa
arXiv:2609.20218v1 Announce Type: cross Abstract: Large language models can label a tabular row from a plain-English description with no training - a capability now shipping in mainstream spreadsheet
arXiv:2609.19213v1 Announce Type: cross Abstract: In this paper, we introduce layer-wise curriculum learning for efficient LLM compression. The proposed method facilitates the knowledge transfer from
arXiv:2609.20530v1 Announce Type: new Abstract: We present Relational BabyLM, a system submission to the BabyLM 2026 challenge that combines two cognitively motivated inductive biases in a single deco
arXiv:2609.20330v1 Announce Type: new Abstract: Blind and low-vision users often need to locate a specific personal object rather than an arbitrary instance of the same category. The task calls for a
arXiv:2609.20455v1 Announce Type: new Abstract: External skills provide domain procedures without parameter updates, but existing methods often edit skills directly from failed rollouts without struct
arXiv:2609.20519v1 Announce Type: new Abstract: As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into lon
Reuters: Sources: Anthropic considers releasing a new AI model to counter OpenAI's momentum since Astra's launch, ahead of an IPO and after Amodei's call for a slowdown — Anthropic is considering roll
I'm trying to find out whether back-and-forth between two different LLMs improves task success beyond strong alternatives under a controlled resource budget — and I'd rather hear that it's already set
Wow, check out this DuckTales theme as a three-voice fugue in the style of Bach's Well-Tempered Clavier. My AI music theory system, which consists of a Rust CLI tool called mtdt and an agent skill lib
arXiv:2609.18094v1 Announce Type: cross Abstract: Autonomous research loops such as AutoResearch show that one coding agent can improve a training setup unattended. Run several of them and each sessio
arXiv:2609.18052v1 Announce Type: cross Abstract: This study empirically evaluates whether cost-efficient Large Language Models (LLMs) can be trusted to generate enterprise code to a written specifica
arXiv:2609.18736v1 Announce Type: new Abstract: Despite recent advances in large language models (LLMs), performing logically consistent deductive reasoning over extended interactions remains challeng
arXiv:2609.18706v1 Announce Type: cross Abstract: Neural decompilers can recover readable and recompilable source code from binaries, but their predictions remain difficult to trust. Matching decompil
arXiv:2608.28363v2 Announce Type: replace Abstract: LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. Such self-evolution can improve
arXiv:2609.18989v1 Announce Type: new Abstract: How many dimensions does a language model's computation actually use? The question is ill-posed until one names a functional. Task-weighted charts make
arXiv:2609.17547v1 Announce Type: new Abstract: AI assistants are expected to remain useful during difficult interactions, but little is known about how repeated verbal abuse changes their engagement
arXiv:2609.19107v1 Announce Type: new Abstract: Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can mo
arXiv:2609.18274v1 Announce Type: cross Abstract: Classroom observations are widely recognized as a key tool for establishing benchmarks of education quality and guiding pedagogical improvement, yet t
arXiv:2609.18959v1 Announce Type: new Abstract: LLM code-generation systems usually choose a target programming language before decoding and treat that choice as fixed. We show that, for language-flex
arXiv:2603.06084v2 Announce Type: replace Abstract: Large language models have been widely used for robotic task planning, often taking advantage of representations such as Behavior Trees (BTs). Visio
arXiv:2609.18007v1 Announce Type: cross Abstract: Text-to-image generative models are widely used in professional and creative settings, yet how they represent gender across occupations -- and whether
arXiv:2505.23126v5 Announce Type: replace Abstract: Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrangl
arXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent log(N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secre
arXiv:2609.18805v1 Announce Type: cross Abstract: Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical web development, however, agents ma
arXiv:2609.18985v1 Announce Type: new Abstract: Knowledge-editing benchmarks certify local correctness, whether an edited model produces the new fact on near-edit prompts but not how much of the origi
arXiv:2609.17575v1 Announce Type: new Abstract: Sharpness-aware minimization (SAM) doubles the cost of every training step, yet its benefit concentrates where training ends. We study where an expensiv
arXiv:2512.24100v2 Announce Type: replace Abstract: Current state-of-the-art paradigms predominantly treat Text-to-Motion (T2M) generation as a direct translation problem, mapping symbolic language di
arXiv:2609.18435v1 Announce Type: new Abstract: Automating biological research requires general-purpose, reproducible robot systems that allow individual wet-lab researchers to delegate robot tasks wi
arXiv:2609.17977v1 Announce Type: new Abstract: Emotion recognition in conversation (ERC) is a production capability behind agent-assist prompts, escalation routing, and post-call analytics in contact
arXiv:2609.18731v1 Announce Type: new Abstract: Bridging the gap between human intent and machine execution remains a challenge in automated planning, where expressing goals in formal languages like P
arXiv:2609.19006v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Large Reasoning Models (LRMs) are typically evaluated on challenging benchmarks through dataset accuracy alone, provi
arXiv:2609.16793v1 Announce Type: cross Abstract: People increasingly reason with large language models (LLMs), yet complementary capabilities do not guarantee outperforming both components. In a betw
Banger report from Salesforce. Pretty interesting to see more of these custom enterprise models. Salesforce trained the enterprise agent model from the same files it uses to configure agents. Koa star
GoBench evaluates LLMs on 9x9 Go games against a ladder of KataGo opponents, from random to superhuman. It measures general reasoning ability, strongly correlates with ARC-AGI 2 (r=0.83 correlation),
Just went on BBC TV and they opened with clips today from Altman, Huang, and Sanders. Altman and Huang want us to believe that the AI companies have the public interest at heart and will happily just
MLPerf Inference v6.1 introduced the first agentic workload run on datacenter hardware and evaluated a model with more than one trillion parameters (Kimi K2), setting a new benchmark for scale. The te
arXiv:2609.16010v1 Announce Type: new Abstract: The complexity of legal language and limited accessibility to legal information pose significant challenges to justice delivery in Nepal. Traditional le
arXiv:2609.16887v1 Announce Type: new Abstract: Long-horizon reasoning is vulnerable to early errors that compromise later decisions. We present QART, the Quantum-Augmented Reasoning Transformer, a qu
arXiv:2609.15998v1 Announce Type: new Abstract: Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property o
arXiv:2609.15991v1 Announce Type: new Abstract: Standard subword tokenizers either treat every orthographic variation of a word (such as hello, Hello, HELLO, and Hello) as unrelated vocabulary entries
With the recent Nvidia Huggingface acquisition and frontier AI labs screaming about safety and putting guardrails everywhere, I think it's important that we have local models that aren't affected by a
arXiv:2609.16179v1 Announce Type: cross Abstract: Z-loss has been widely applied to the logits of language-model output heads and sparse mixture-of-experts routers. Z-loss constrains the softmax log-n
arXiv:2609.15007v1 Announce Type: new Abstract: Large language models are increasingly used as natural-language interfaces to structured data, yet they remain unreliable when answers require consisten
arXiv:2607.18063v2 Announce Type: replace-cross Abstract: LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. We present a 21-scenario benchmark f
arXiv:2603.19574v2 Announce Type: replace-cross Abstract: Conversational AI systems are increasingly used for personal reflection and emotional disclosure, raising concerns about their effects on vuln
arXiv:2404.03028v4 Announce Type: replace Abstract: Modern language models (LMs) can learn to perform new tasks in different ways: in instruction following, the target task is described explicitly in
arXiv:2609.15511v1 Announce Type: cross Abstract: This paper investigates the generation and human evaluation of Japanese haiku by contemporary Large Language Models (LLMs), focusing on authorship per
arXiv:2609.15706v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to extract structured fields from business documents, yet most evaluations report accuracy on clean
arXiv:2609.14988v1 Announce Type: new Abstract: Background. Large language models are increasingly used to help write biomedical text but may fabricate references to nonexistent work. How often large
arXiv:2609.13149v1 Announce Type: cross Abstract: For local large language model agents, active context is a scarce resource: memory capacity, prefill latency, cache growth, and service objectives all
arXiv:2609.15142v1 Announce Type: new Abstract: Zero-shot vision-and-language navigation in continuous environments (VLN-CE) increasingly places foundation vision-language models (VLMs) inside the nav
arXiv:2511.13725v5 Announce Type: replace-cross Abstract: Malicious AI causing harm to humans is not just a Hollywood fantasy. Indeed, as highly capable models such as Claude Mythos emerge and agent s
arXiv:2510.09302v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success in difficult purely textual mathematical reasoning tasks, even
arXiv:2609.15668v1 Announce Type: cross Abstract: Through pre-training on extensive text and image datasets, current multi-modal large language models (MLLMs) achieve strong performance on general tas