adding-irrelevant-tokens-alone-degrades-reasoning-mechanism-by CLM-0016
mechanismsingle paperReviewed by AI and Russ Miller

Adding irrelevant tokens alone degrades reasoning, which is the mechanism by which a bloated context hurts an agent.

Evidence for: Lehman's law of increasing complexity (holds)

Capability: Keeping its own context clean

Sources

Reviewed by AI and Russ MillerLast checked: 2026-09-03Evidence activityHow much the field cites the sources under this claimheavily cited in the last 12 months104 in 12mo · 238 total — Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
Either way, bring evidence: a link, or what you saw.

Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.