3 papers
cs.AI2026
Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations
Jessica Tang, Shraddha Barke, Sharad Agarwal
When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies propagate across prior turn…
cs.AI2026
WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics
Madhav Kanda, Sharad Agarwal, Rodrigo Fonseca +2
Multi-agent LLM systems that generate structured workflows from natural-language requests are now deployed in production across cloud automation, DevOps, and enterprise process orc…
cs.AI2026
Switchcraft: AI Model Router for Agentic Tool Calling
Sharad Agarwal, Pooria Namyar, Alec Wolman +3
Agentic AI systems that invoke external tools are powerful but costly, leading developers to default to large models and overspend inference budgets. Model routing can mitigate thi…