Skip to content

Extreme agent looping: 30-50 tool calls consuming 400K-700K+ tokens across multiple models#558

Draft
langsmith-engine-dev[bot] wants to merge 1 commit into
masterfrom
issues-agent/9b985c00-b200-4e76-ada8-de182821c33a
Draft

Extreme agent looping: 30-50 tool calls consuming 400K-700K+ tokens across multiple models#558
langsmith-engine-dev[bot] wants to merge 1 commit into
masterfrom
issues-agent/9b985c00-b200-4e76-ada8-de182821c33a

Conversation

@langsmith-engine-dev
Copy link
Copy Markdown
Contributor

Multiple traces show the agent making 30-50 tool calls with repeated identical queries, consuming 400K-700K+ tokens and taking 150-300+ seconds. This is a more severe variant of the Gemini looping pattern and affects multiple models including GPT-5 Mini. The worst case (019d73be) made 50 tool calls repeatedly searching "composite", "evaluator", and "LangSmith Evaluation" for a Korean-language question about annotation queues. The recursion_limit in langgraph.json is set to 100, which is far too high to prevent this. Reducing it to 20-30 and adding tool call deduplication would prevent these extreme cases.

…ooping

Traces show the agent making 30-50 tool calls with repeated identical queries,
consuming 400K-700K+ tokens. The recursion_limit of 100 allows far too many
iterations. A limit of 25 (~10-12 tool call rounds) is sufficient for any
legitimate question while preventing runaway loops.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants