Event date · · Z.ai

GLM-4.7 Released: Preserving Reasoning State Across Tool Steps for Long-Chain Coding Agents

FACT STATEMENT

Zhipu AI released and open-sourced GLM-4.7 weights in December 2025, focusing on enhanced coding, tool use, and multi-step reasoning.

What happened

GLM-4.7 pushes the competitive frontier to state preservation during multi-turn agent execution: the model needs to reuse existing reasoning across consecutive tool calls rather than restarting each step.

Technical significance

The official introduction describes Interleaved Thinking, Preserved Thinking, and Turn-level Thinking, enabling the model to think before tool calls, retain thinking blocks across turns, and control reasoning budget per turn.

Industry impact

The bottleneck for coding agents has shifted from single-generation quality to long-chain consistency, state compression, and failure recovery; model interfaces are also beginning to expose finer-grained reasoning control.

Decision value

Engineering teams should decompose tasks into auditable stages and check whether preserved state reduces redundant work, while avoiding carrying untrusted intermediate reasoning into subsequent steps over long periods.

What to watch

Observe the real impact of preserved reasoning on token cost, error accumulation, privacy leakage, and long-task success rate.

DECISION BRIEF

Turn the evidence into a decision.

See how AIGC.NEWS separates verified change, judgment, and the next signal to watch.