Never Stop Thinking: Continuous-Time Language Agents
Quick summary
arXiv:2609.17416v1 Announce Type: new Abstract: Voice agents built on LLMs follow a rigid listen-think-speak loop that inserts seconds of dead air before every reply. We show that continuous-time cognition (thinking while listening and thinking while speaking) emerges from an unmodified text model under a lightweight interrupt-and-resume orchestrator, cutting live-pipeline latency by 19% overall and by half in the regime the mechanism targets. To measure whether continuous-time thinking improves what agents accomplish, we introduce ReactiveBench: 120 interactive scenarios scored against pre-re
Key takeaways
- arXiv:2609.17416v1 Announce Type: new Abstract: Voice agents built on LLMs follow a rigid listen-think-speak loop that inserts seconds of dead air before every reply.
- We show that continuous-time cognition (thinking while listening and thinking while speaking) emerges from an unmodified text model under a lightweight interrupt-and-resume orchestrator, cutting live-pipeline latency by 19% overall and by half in the regime the mechanism targets.
- To measure whether continuous-time thinking improves what agents accomplish, we introduce ReactiveBench: 120 interactive scenarios scored against pre-re
Why it matters
“Never Stop Thinking: Continuous-Time Language Agents” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments