arXiv:2610.30705v1 Announce Type: new Abstract: Text embedding and text generation are two of the most useful capabilities of modern large language models, yet they are typically provided by separate specialized models (an embedder and a generator) trained with incompatible objectives and deployed side by side in retrieval-augmented generation and agent systems. Recent unified embedding-generation models such as GritLM share parameters between the two capabilities, but they either switch attenti
arXiv:2610.30715v1 Announce Type: new Abstract: This paper studies the local geometry of semantic meaning in large language models. Current representation analyses ask whether meanings are close in embedding space, or whether linear probes separate semantic classes, but they do not characterize the within-concept local geometry: what is invariant across realizations of a single semantic factor, what varies, and what changes when meaning is refined. This paper characterizes that geometry through
arXiv:2610.30742v1 Announce Type: new Abstract: Guardrail models are increasingly used as safety layers for LLMs and agentic systems, but most are trained on fixed prompt or response interfaces and become unreliable when the same safety case appears as a conversation, agent trajectory, multi-agent trace, or policy-conditioned input. We propose UniGuard, a training framework that learns interface-invariant safety representations from multiple semantically aligned views of the same safety case. We
arXiv:2610.30778v1 Announce Type: new Abstract: Do people who speak different languages organize concepts in similar ways? This question lies at the heart of the Sapir--Whorf hypothesis and debates about linguistic relativity. Shared basic meanings, however, need not imply shared relations among them. We compared relations among 196 basic concepts across 81 languages, using word embeddings from two multilingual models to quantify conceptual structure expressed in language. Cross-language corresp
arXiv:2610.30785v1 Announce Type: new Abstract: Language models are aligned to avoid using protected attributes such as race, ethnicity, and gender to inform their responses. Therefore, they increasingly refuse or hedge when such attributes appear in a prompt. However, if a system must decide how much to learn from what people tell it, it is costly to refuse valuable information because of its source. In this article, we measure the cost of declining information in a two-urn game with an exact B
arXiv:2610.30828v1 Announce Type: new Abstract: LLMs are increasingly used as AI tutors, yet existing benchmarks overlook the challenging behaviors common among students with learning and behavioral difficulties. We introduce TutorCaseBench, a benchmark that grounds AI-tutor evaluation in qualitative case studies from pedagogy, educational psychology, and special education. Our pipeline converts documented student categories into case-specific scenarios, tutor-student dialogues, and rubrics grou
arXiv:2610.30841v1 Announce Type: new Abstract: Ambiguity is a central feature of natural communication: a sentence, image, or sound may remain underspecified until evidence from the other channels is considered. Yet current multimodal benchmarks mostly test perception, recognition, or reasoning over already determinate inputs, leaving unclear whether omni-modal large language models can resolve ambiguity distributed across text, vision, and audio. We introduce TRIAD, a benchmark for omni-modal
arXiv:2610.30860v1 Announce Type: new Abstract: Nepali-English code-switched conversational speech presents severe challenges for automatic speech recognition (ASR), chiefly through script confusion (inappropriate mixing of Devanagari and Latin orthography) and elevated error rates at language switch points. Supervised fine-tuning (SFT) can adapt multilingual foundation models, but human code-switched audio is expensive to collect and annotate. We curate a new benchmark of 13,044 spontaneous pod
Release: battledrones v14: Compass Rose, a four player map I added four player online mode to Battledrones - previous maps were limited to two. Here's the initial prompt I used: Add a new map for a four player battle - four way rotational symmetry, up to four AI players, works with the WebSocket non-audio based multiplayer mode so up to four human players can join (any spare slots use AI) Claude Opus 5.5 added a new map called "Compass Rose" and modified the WebSockets multiplayer network code t
Changes since 1.2.16 release(langgraph): 1.2.17 ( #9418 ) fix(langgraph): apply an explicit recursion_limit equal to the default ( #9417 ) fix(langgraph): keep the caller's namespace in RemoteGraph.stream(subgraphs=True) ( #9401 ) chore(deps): remove precautionary third-party upper bounds ( #9390 ) chore(deps): bump certifi from 2026.1.4 to 2026.10.19 in /libs/langgraph ( #9375 ) chore(deps-dev): bump the minor-and-patch group in /libs/prebuilt with 6 updates ( #9150 )
12 angry men is a very thought-provoking film, and there is nothing quite like it. Its premise is just 12 people sitting in the jury room and sharing their experiences and judgment on a very sensitive case. They need to decide whether a boy is innocent or guilty of a crime. I have been playing around with a thought experiment where agents play human roles and come to a conclusion. I created agents for each jury, and the judge is another agent that can make an informed decision based on what the
Tool: Quick Study Prompt to Claude Opus 5.5 High : Build an artifact where you open a photo and it rapidly (in a few seconds) paints a version of that photo using a canvas element and simulated paintbrush See also my previous experiment getting Claude Fable to simulate a watercolor illustration with P5.js. Quick Study uses Sobel edge detection , with no external libraries beyond Google Fonts. Tags: tools