The authors address how an agent can turn accumulated interaction histories into reusable memories without retraining its underlying model or consulting gold-standard labels.
RefCon improves agent memory by refining and contrasting past experience
The method uses additional inference-time computation to extract useful memories from noisy trajectories without requiring labeled examples or model retraining.
Chinese Tech
Ubaidillah Ariq Prathama · Bo Liu · Yeo Boon Hong · Yu-Xuan Huang · Yangkai Ding · Tao Yu
Huawei Technologies, Co., Ltd.
Research Digest··2 min read
Thread:Memory Management for Agents
Prathama et al.
Why this paper
From Huawei Technologies, Co., Ltd. · Part of Memory Management for Agents, now 44 papers
In one line
RefCon combines self-refinement and self-contrast to extract higher-quality memories without gold labels.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§