cs.AINov 12, 2026

CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation

Authors: Peiwen Li, Harshit Verma, Sophia Zhou, Haiwen Wang, Ngoc Bui, Heng Chang, Fei Fei, David van Dijk, 

Organizations: Yale University · Tsinghua University · Goodvision AI

Abstract

Coding agents tackle successive tasks on an evolving repository, carrying forward edits and writing memory before the next task is known. Selecting memory for unknown next tasks requires balancing future usefulness against the costs of writing and reading it. The actor must also decide when acting on available memory saves effort as the task unfolds. We introduce Coding-Repository Memory (CoReMem), a cost-internalizing framework that guides memory design and actor adaptation through measured memory value on the next task. Prospective segment valuation compares runs of the next task with and without individual trajectory segments from the same inherited repository state, guiding a compact memory built around anchors: repository locations and executable checks. Actor adaptation estimates on-policy memory value within rollout groups with and without memory, using a reward that prioritizes resolution and penalizes step count in successful runs. Provenance-gated value credit assigns the additional value term to steps identified as using memory-supplied anchors, while every step retains outcome credit. On ChainSWE, CoReMem raises the 27B actor's resolve rate from 21.0% to 25.7%, with 17% fewer steps and 11% fewer total cache-aware tokens, including memory-module calls, relative to the untrained actor model without memory.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. REM: What to Store, When to Recall, What to Forget in Experience Memory for Coding Agents

    Oct 19, 2026Xinyi Lisa Chen, Pedro Herrero-Vidal, Xiaohan Chen +6Memory Management for LLM AgentsAgent Memory

  2. MemCodex: Self-Programming Hierarchical Memory for Language Agents

    Sep 30, 2026Xiaoqiang Wang, Bang LiuAgent Memory ManagementMemory-Augmented Language Model Agents

  3. MemTrace: State-Consistent Memory for Long-Horizon Coding Agents

    Oct 4, 2026Hongming Xu, Le Zhou, ZhongHe Jin +5Agent MemoryAgent Memory Management