Trimming coding agents' history saved money in zero of 42 tests under cache-based pricing

Researchers ran 9,400 experiments with two coding agents to test 42 ways of deleting old conversation history to save money. Under flat per-token pricing, estimated costs fell in 26 of the 42 setups. Under pricing that discounts cached input, none lowered costs, because trimming breaks the cached prefix and agents often re-fetched what was deleted.

Photo: Bair175 / Wikimedia Commons, CC0 (cropped)

Sources

• Research arXiv（査読前） (2026-10-26)
  The Hidden Costs of Forgetting: A Study of Trajectory Deletion in Software Engineering Agents

Editorial policy ・ Terms of use