Live intelligence

Latest AI updates

3 updates
Research Editor selected

Ask on Demand: Targeted Peer Communication for Parallel Agentic Systems

Researchers propose Ask on Demand (AOD), a communication framework that lets parallel LLM agents request targeted assistance from peers only when specific information needs arise. A lightweight gate trained on team outcomes decides when such requests are worthwhile. Experiments on AppWorld and WebShop show AOD improves task performance over independent execution while reducing inference cost compared to existing sharing methods.

Why it matters: Offers a practical, cost-efficient approach to multi-agent collaboration that adapts to agents' evolving information needs.

multi-agent collaborationLLM agent communicationtargeted information sharing
Research Editor selected

MASCAL Trains AI Agents to Share Calibrated Confidence During Collaboration

The paper introduces MASCAL, a reinforcement-learning approach that trains collaborating AI agents to attach calibrated correctness probabilities to their answers. Confidence-aware weighting helps downstream agents learn to use these signals when deciding whether to trust or verify upstream results. Across three collaboration architectures covering Web retrieval and reasoning, the authors report improved accuracy and calibration, with final confidence scores supporting selective answering and targeted rechecking.

Why it matters: The research addresses unreliable handoffs between AI agents with an explicit confidence signal that can inform verification decisions.

MASCALMulti-agent collaborationConfidence calibration
Industry Editor selected

Beyond Harness: JiuwenClaw Unleashes AgentTeam for Seamless Multi-Agent Coordination

The openJiuwen community has officially released the latest iteration of&nbsp;JiuwenClaw, introducing a groundbreaking feature:&nbsp;AgentTeam. This update marks a significant shift from &quot;Harness Engineering&quot; to&nbsp;&quot;Coordination Engi<!--autointro-->

Autonomous AgentsJiuwenClawAgentTeam