Unverified50% confidenceOpinionExact time
推理令牌聚集指推理令牌在分布上出现异常集中或堆叠，导致模型陷入思维定式反复在相似推理路径打转
1
Sources
50%
Confidence
Long-term
Relevance
7/6/2026
First Seen
Sources
GPT-5.5 Codex Reasoning-Token Clustering Explained: Causes of Performance Regression and How to Respond
hackernewshackernews7/4/2026
Related Claims
UnverifiedReasoning models have built-in autonomous decomposition and verification mechanisms, and overly detailed prompts can actually compress the model's reasoning space.73% similarUnverifiedTop-tier models employ techniques such as chain-of-thought or extended reasoning, generating a large number of intermediate tokens during inference, causing per-call token consumption to be several times that of ordinary models.72% similarUnverifiedThe Kimi model occasionally falls into lengthy reasoning token loops when using chain-of-thought reasoning, oscillating back and forth between two mutually contradictory conclusions.70% similarUnverified思维链推理的效果随模型规模呈现涌现性，在较小模型上几乎无效，在足够大的模型上才能显著提升推理准确率70% similarUnverified现代推理模型通常具备推理预算机制，为每次推理分配一定量的令牌配额69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/112825API
curl https://kongchang.com/api/v1/knowledge/claims/112825MCP
get_claim(id=112825)