Compaction beats full transcript in memory
Compaction scores 71.4 percent vs 64.6 percent with 34 percent fewer tokens on LoCoMo.
Stories per day · 30 days
3 RSS
Relateddataset1herhealthgpt1instruction-tuning1language-models1legal-ai1llm-evaluation1memory-compaction1modernbert1rag1reproductive-health1retrieval1retrieval-augmented-generation1system-prompts1wildchat1
15 stories, newest first · one card per story
Stories tagged #conversational-ai
HerHealthGPT grounds reproductive-health answers in retrieval and clarification
On 540 messages from 90 cases, retrieval lifted concern-category accuracy from 54.1% to 59.3%.
Paper frames instruction-tuned models as an instructional-conversational genre
The argument ties the genre to instruction fine-tuning, system prompts, special tokens and role-based turn-taking.
Study maps how WildChat users ask LLMs for legal guidance
In an enriched sample, 71.1% of legal-content chats sought personalized or practical guidance; annotations are public.
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
RealCompanion benchmarks whether agents truly use months of real companion chats to understand a person.
REALM: A Coarse-to-Fine Generative Framework for Embodied Reactive Listening
REALM generates reactive listener facial motion with coarse trajectories plus stochastic expression residuals, including Ameca deployment.
PUBG Ally: A Conversational Embodied Agent as an AI Teammate
Researchers present PUBG Ally, a voice-enabled embodied teammate trained on nearly 39,000 live PUBG sessions.
YouTube Music gets more conversational with new AI features
YouTube Music is adding conversational Ask Music and an AI podcast discovery guide.
1
Gricea: An Open Science Platform for Conversational AI Research
Gricea packages conversational-AI studies as reusable artifacts and shows most papers omit replication details.
Gricea: An Open Science Platform for Conversational AI Research
Gricea packages conversational AI studies as runnable, shareable research artifacts, replicating 93% of eligible CUI 2026 paper configurations.
Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agents
Duplex Cue evaluation shows PersonaPlex full-duplex agents adapt in-turn to listener contributions in only 34.8% of collaborative cases versus 68.2% for humans.
MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant
MP-Bench is the first benchmark for voice agents in multiparty conversations, finding real-time agents near chance on turn-taking.
Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models
Researchers release Explainability Assistant, an open-source conversational XAI tool using LLM function calling, lifting intent-parsing accuracy from 76.8% to 94%.
What Did I Just Say? Self-Listening for Full-Duplex Speech Models
Researchers propose Self-Listening, a full-duplex speech approach feeding realized model speech back as input to improve interruption recovery.
What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation
A new benchmark shows LLMs reach 68.3-93% accuracy propagating local revisions across conversationally generated artifacts, with parallel-sample selection most cost-effective.