Skip to content

Author

Yan-Biao Ma

5 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression

Results characterize agent reasoning as dynamic working state rather than permanent interaction history, and suggest that historical reasoning becomes more replaceable once task relevant derived state has been reliably externalized into code, files, tool outputs, or environmental feedback.

Ming-Xuan Wang, Fei Luo, Bo Wang et al. · 4 citations
#artificial intelligence Preprint Sep 2026

Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression

Geometry Guided Evidence Preserving Memory (GEM), a training free compressor that protects task and execution evidence before using geometric residuals to complete coverage, is introduced, showing that efficient agent history compression should optimize for preserved task evidence rather than geometric coverage alone.

Ming-Xuan Wang, Fei Luo, Bo Wang et al. · 0 citations

StateComp: Learning When to Compress History in Long Horizon Agents

This work proposes State Conditioned Compression (StateComp), a framework that determines when historical interactions can be safely compressed according to the current agent state, and demonstrates that it reduces total agent and summarization tokens while maintaining task performance, and achieves a 12.67-fold speedu...

Ming-Xuan Wang, Hong-Yue Chen, Ying-Long Guo et al. · 3 citations
#artificial intelligence Preprint Sep 2026

Memory Control Signals Emerge Before Action in Long Horizon Agents

The hidden state immediately before each agent action is studied and it is found that compression and recall needs are already encoded in the model's internal representations, which substantially reduces context consumption while maintaining competitive task performance.

Ming-Xuan Wang, Guo-Run Yao, Fei Luo et al. · 0 citations
#small language model Preprint Sep 2026

DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents

Direct Relational Set-Risk Pruning is introduced, which formulates agent-history compression as risk-constrained selection over deletion sets and shows that decision-conditioned relations, retained-context information, pair interactions, and abstention each contribute to reliable pruning.

Ming-Xuan Wang, Bo Wang, Fei Luo et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.