Knowledge catalogue
arXiv:2609.27262v1 Announce Type: new Abstract: Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or
Zapier reports 97% daily-work AI use and says its AI support-ticket summarizer halved average handle time.
DoorDash and AWS describe a live Bedrock-backed voice agent for Dasher support, reporting hundreds of thousands of calls daily.
Sun Life says its internal GenAI chatbot had over 5,000 weekly users and 400,000 queries in its first eight months.
arXiv:2610.11370v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) grounds language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolate
arXiv:2609.21187v1 Announce Type: new Abstract: Agent models are frequently evaluated one decision at a time, where the model predicts the next action based on the gold interaction history, which is s
arXiv:2609.05758v2 Announce Type: new Abstract: Conversational assistants can blend retrieval, action selection, escalation, and wording in a single model path, or separate those roles. We report a pr
arXiv:2608.24076v1 Announce Type: new Abstract: Evaluation of agentic information retrieval remains limited to scripted interactions with uniform users, missing both natural personality diversity and
arXiv:2608.20393v1 Announce Type: cross Abstract: Agentic large language models (LLMs) deployed in fact-sensitive applications such as customer support must simultaneously preserve factual correctness
arXiv:2608.02616v1 Announce Type: cross Abstract: We present the first independent, systematic evaluation of OpenAI's Privacy Filter (OPF), a 1.5B-parameter bidirectional PII detector, across 42 synth
arXiv:2605.30628v1 Announce Type: cross Abstract: Universal LLM reliability is not a finite-library problem: across all possible tasks, tools, schemas, knowledge sources, and evaluator expectations, n
arXiv:2604.14572v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a passive consumer of search results: it never