# RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent

arXiv: https://arxiv.org/abs/2609.39143 · HTML: https://mlsanity.com/paper/2609.39143/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle](https://mlsanity.com/paper/2510.16079/) (2025)
- [Inducing Programmatic Skills for Agentic Tasks](https://mlsanity.com/paper/2504.06821/) (2025)
- [Reinforcement Learning for Self-Improving Agent with Skill Library](https://mlsanity.com/paper/2512.17102/) (2025)
- [Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution](https://mlsanity.com/paper/2512.10696/) (2025)
- [Training-Free Group Relative Policy Optimization](https://mlsanity.com/paper/2510.08191/) (2025)
- [StreamBench: Towards Benchmarking Continuous Improvement of Language Agents](https://mlsanity.com/paper/2406.08747/) (2024)
- [General Agentic Memory Via Deep Research](https://mlsanity.com/paper/2511.18423/) (2025)
- [Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecture](https://mlsanity.com/paper/2512.11303/) (2025)
- [Experience-Guided Adaptation of Inference-Time Reasoning Strategies](https://mlsanity.com/paper/2511.11519/) (2025)

## Abstract (arXiv)

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.