Live intelligence

Latest AI updates

6 updates
Research Editor selected

Persistent Retrieval Subagent Cuts Token Use and Cost in Conversational Agents

This paper compares three retrieval designs for conversational agents: skill-based retrieval, non-persistent subagent, and a persistent retrieval subagent that maintains history across turns. The persistent approach reduces token usage by 43.3% and API cost by 45.0% versus skill-based retrieval, while also cutting response time by 9.1%. It shifts the subagent's role from synthesizing answers to maintaining state and supplying evidence for the main agent.

Why it matters: Provides concrete efficiency gains for a common agent architecture, offering actionable design insights for developers building conversational AI systems.

retrieval-augmented generationagent designconversational AI
Research Editor selected

New Evaluation Separates AI Agents’ Conversation Retrieval, Re-engagement and Continuity

Researchers introduce a framework for evaluating whether LLM agents can find inactive conversations, autonomously return to them and reconstruct enough context for coherent continuation. Across six LLM configurations, conversational resurfacing improves target conversation identification, while persistent memory is associated with more autonomous target-directed replies. Neither produces consistent improvements in contextual reconstruction, suggesting that retrieval and re-engagement need to be evaluated separately from conversational continuity.

Why it matters: The study gives agent developers a concrete framework for testing long-term conversational capabilities that memory retrieval metrics alone may miss.

AI agentsLong-term memoryAgent evaluation
Research Editor selected

Simulation-based reinforcement learning improves AI psychiatric intake in role-played encounters

An arXiv preprint reports that multi-turn reinforcement learning in simulation improved a language model’s structured psychiatric intake performance compared with its identically prompted base model. In 120 encounters with psychiatrists role-playing standardized patients, independent psychiatrist evaluators preferred the trained agent in 76.7% of matched scenario pairs, with improvements in communication and differential diagnosis. In adversarial simulated presentations, under-triage of acute safety risks fell from 30.5% to 12.9%; the findings do not establish effectiveness with real patients, and residual gaps require safeguards and clinician oversight.

Why it matters: The study provides concrete evidence that simulation-based training can improve psychiatric conversational agents while highlighting safety limitations and the gap between role-played evaluation and real-world care.

Reinforcement learningPsychiatric intakeConversational AI
Industry Editor selected

Four Generations of the Rapidflare Agent Harness: Spark, Flame, Blaze, and Forge

How the Rapidflare Agent Harness Has Evolved Across Four Generations — From a Simple RAG Pipeline in 2023 to a Long-Running, Broader, Deeper Harness in 2026This blog post was originally published on Rapidflare&#39;s website. It is reprinted here with<!--autointro-->

enterprise AIconversational AIRapidflare agent harness
Industry

Meet Shapes: The Social App Where Humans and AI Chat Together in Group Conversations

Shapes, a social messaging app that brings humans and AI characters together in shared group chats, has raised $8 million in seed funding and officially emerged from stealth.Founded in 2022, Shapes now has over 400,000 monthly active users. The app a<!--autointro-->

conversational AIAI group chathuman-AI interaction
Industry

YouTube Tests &quot;Ask YouTube&quot;: A New AI-Powered Chat Interface for Search

YouTube is currently testing a significant update to its search functionality, introducing an AI-driven chat interface designed to provide more direct and interactive answers. This new feature, referred to as &quot;Ask YouTube,&quot; shifts the user <!--autointro-->

conversational AIGoogle AIYouTube AI search