Abstract
Long-horizon agent interactions generate useful but noisy experience, and retraining models to absorb it is expensive. Context-evolving agents therefore need memory extraction methods that improve with more test-time compute without relying on gold labels. We propose RefCon, which combines sequential self-refinement with parallel self-contrast to extract higher-quality memories without gold labels. Evaluated on AppWorld and BFCL-V3 across multiple context-evolving agent frameworks, RefCon delivers strong and consistent gains, including relative improvements of 21.6% on ACE and 16.6% on ReMe over no-scaling baselines, while a diversity-focused variant (DivCon) achieves a 35.5% gain on ReasoningBank. RefCon consistently outperforms existing baselines without ground-truth labels, and generalizes across model scales and to software engineering tasks, where it surpasses even ground-truth baselines. We further analyze the accuracy-token trade-off and scaling behavior, showing RefCon maintains favorable efficiency and continues to improve as more trajectories are used, unlike diversity-only scaling which saturates earlier.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Prathama, U. A., Liu, B., Hong, Y. B., Huang, Y. X., Ding, Y., & Yu, T. (2026). RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent. https://omanscience.com/en/articles/refcon-iterative-refinement-and-contrastive-memory-extraction-for-context-evolving-agent
MLA 9
Prathama, Ubaidillah Ariq, et al. "RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent." https://omanscience.com/en/articles/refcon-iterative-refinement-and-contrastive-memory-extraction-for-context-evolving-agent.
Chicago (author–date)
Prathama, Ubaidillah Ariq, Bo Liu, Yeo Boon Hong, Yu-Xuan Huang, Yangkai Ding, and Tao Yu. 2026. "RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent." https://omanscience.com/en/articles/refcon-iterative-refinement-and-contrastive-memory-extraction-for-context-evolving-agent.
Harvard
Prathama, U. A., Liu, B., Hong, Y. B., Huang, Y. X., Ding, Y. and Yu, T. (2026) 'RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent', Available at: https://omanscience.com/en/articles/refcon-iterative-refinement-and-contrastive-memory-extraction-for-context-evolving-agent.
Vancouver
Prathama UA, Liu B, Hong YB, Huang YX, Ding Y, Yu T. RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent. https://omanscience.com/en/articles/refcon-iterative-refinement-and-contrastive-memory-extraction-for-context-evolving-agent
IEEE
U. A. Prathama, B. Liu, Y. B. Hong, Y. X. Huang, Y. Ding, and T. Yu, "RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent," https://omanscience.com/en/articles/refcon-iterative-refinement-and-contrastive-memory-extraction-for-context-evolving-agent.