Tag
Skopx is a conversational AI analytics platform that lets users ask business questions in plain English, automatically generating insights from connected data sources without SQL. It provides transparent reasoning, role-based access, and integrates with existing tools.
OpenAI has launched three new real-time audio models to enable continuous, multitasking voice interactions that prioritize long-context reasoning, live translation, and seamless tool use.
PersonaKit is an open-source web platform designed for rapid prototyping and user testing of diverse personas in full-duplex dialogue systems. It allows researchers to configure persona-specific turn-taking behaviors via JSON and conduct A/B surveys to evaluate sociolinguistic interactions.
Lyzr Cognis introduces a unified, open-source memory system for conversational AI that fuses BM25 and Matryoshka vector search with version-aware ingestion, achieving SOTA on LoCoMo and LongMemEval benchmarks.
Study shows GPT and Claude exhibit distinct, unreliable repair behaviors in multi-turn math dialogues, with some models resisting correction and others over-correcting.
This position paper argues that audio misinformation on platforms like podcasts and WhatsApp voice notes is structurally different from text-based misinformation, carrying unique persuasive properties through prosody and conversational dynamics that existing fact-checking pipelines fail to address. The authors call for a rethinking of verification pipelines tailored to the spoken and conversational nature of audio media.
A developer built a V2 AI chat assistant that autonomously manages their direct messages, featuring web search, image reading, voice note transcription, GIF sending, memory of past conversations, and automatic follow-ups. The tool has processed ~500k tokens across ~500 messages, raising questions about authentic social interaction.
MoshiRAG combines a compact full-duplex speech language model with asynchronous retrieval-augmented generation to improve factuality while maintaining real-time interactivity. The approach leverages natural temporal gaps in conversation to retrieve external knowledge without disrupting the natural flow of dialogue.
MTR-DuplexBench introduces a comprehensive benchmark for evaluating Full-Duplex Speech Language Models in multi-round conversations, addressing challenges like blurred turn boundaries and context inconsistency while assessing conversational features, dialogue quality, instruction following, and safety.
This paper introduces the one-sided conversation problem (1SC), addressing how to reconstruct missing dialogue and generate summaries when only one speaker's turns are available in real-world settings like telemedicine and call centers. The authors evaluate prompting and finetuned models on multiple datasets, finding that access to future context and utterance length information improves reconstruction, while high-quality summaries can be generated without full dialogue reconstruction.
This paper analyzes spontaneous dyadic Zoom conversations using multimodal features (acoustic, facial, turn-taking) to identify markers of perceived conversational success, finding that entrainment in speech and facial movements correlates with higher interaction quality.
This paper proposes multi-strategy utterance generation methods for Emotional Support Conversations (ESC), where each utterance can contain multiple strategy-response pairs. Two generation approaches (All-in-One and One-by-One) enhanced with cognitive reasoning via reinforcement learning are evaluated on the ESConv dataset, demonstrating improved supportive quality and dialogue success.
ClankerPass is a product that challenges users to convince an AI that they themselves are an AI, a reverse Turing test-style interaction.
Tines launches Story Copilot, a chat-based interface for building intelligent security workflows without code.
An introductory guide to using ChatGPT, covering basic prompting techniques, practical use cases, and voice/dictation features to help new users get started with the conversational AI assistant.
ServiceNow introduces EVA, a new end-to-end evaluation framework for conversational voice agents that jointly scores task accuracy and conversational experience.
OpenAI releases GPT-5.3 Instant, an update to ChatGPT's most-used model that improves conversational flow, reduces unnecessary refusals, and decreases hallucinations by up to 26.8% in high-stakes domains. The update focuses on tone, relevance, and practical usability based on user feedback.
Sneo.ai lets users chat with their SEO data to extract insights conversationally.
TRUSTBANK has integrated AI agents powered by OpenAI's API into its Furusato Choice platform to help users personalize hometown tax donation gifts through conversational recommendations and intelligent search.
Praktika is an AI-powered language learning app that uses a multi-agent system with GPT-5.2 and GPT-5 Pro to provide personalized conversational lessons that mimic real human tutors through adaptive lesson delivery, progress tracking, and dynamic learning planning.