Blog
Writing
Life, tech, and everything in-between.
The Tool-Calling Agent Loop: ReAct as It Actually Ships
7 minAI
The 2022 ReAct paper parsed thought-action-observation from free text. Production agents today use native tool-calling, a step budget, input and output guardrails, and explicit handoff handling. The simple loop earns its hardening.
ReAct: Reasoning and Acting in One LLM Loop
6 minAI
The foundational agent pattern from Yao et al. interleaves a short reasoning trace with a single tool call, then folds the observation back into the next step. Simple in shape, strong on grounded reasoning benchmarks.