arXiv:2608.22762v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large Language Models…
Tag: AI
Gamma acquires Accel-backed design startup Lica
Lica co-founders are going to work on Gamma’s new research team.
TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts
arXiv:2608.22788v1 Announce Type: new Abstract: Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning…
Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC
This post has no text preview — click the link below to read the original article. This article has been indexed from Hugging Face – Blog Read the original article: Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo…
Performance of a domain-specific large language model in answering patient questions in psychiatry
arXiv:2608.22797v1 Announce Type: new Abstract: Background This study was designed to evaluate whether a domain-specific large language model (LLM)…
Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf
arXiv:2608.22697v1 Announce Type: new Abstract: Search rankings are valuable because human attention is scarce and sequential. Higher-placed alternatives…
LLM-Based Selection of Incongruent Verbal and Nonverbal Behavior for Virtual Humans
arXiv:2608.22731v1 Announce Type: new Abstract: Nonverbal behavior generation systems for virtual agents often take an utterance as input and generate…
Robustness Analysis of Agentic AI to Inconsistent and Incomplete Tool Responses
arXiv:2608.22676v1 Announce Type: new Abstract: Robustness to a bad tool return means answering it in the way that return calls for, which depends on how…
CacheRouter: A Dual-Path Tool Routing Architecture with Cache-Preserving Main-Model Isolation for Long-Tail Tool Discovery
arXiv:2608.22708v1 Announce Type: new Abstract: Tool use in LLM systems faces a structural trade-off. Progressive disclosure keeps the prompt small by…
OpenAI’s Jalapeño chip is built for fast inference at scale, benchmarks show
Tested on Semianalysis’s InferenceX benchmark, Jalapeño registered both more tokens per user and more throughput per kilowatt than the currently available…