Long horizon agents accumulate growing interaction histories that increase context and inference costs. We find that geometric redundancy alone is an insufficient criterion for safe compression. Altho...
The paper investigates how long‑horizon language model agents encode memory‑management signals before taking actions. By examining hidden states just prior to each action, the authors find that the model already signals the need for compression and recall, independent of context length or interaction progress, and that these signals vary across model depth. They propose the Preaction Memory with Evidence Retrieval (PaMER) framework, which uses state‑guided compression and selective evidence retrieval to reduce context consumption while preserving task performance.
By Mingxuan Wang, Guorun Yao, Fei Luo, Yinglong Guo, Chao Ning, Bo Wang, Hongyue Chen, Yanbiao Ma, Jungong Han
SUMONE is a lightweight summarizer designed to compress long interaction histories of language‑model agents. It is trained via masked reconstruction, where a frozen reconstructor predicts randomly masked parts of the original trajectory; reconstruction quality plus a length penalty yields a task‑agnostic reward for optimizing the summarizer with GRPO. At inference, only the summarizer remains, enabling plug‑and‑play context compression that reduces inference cost by roughly 78 % on DeepSearchQA and 75 % on SWE‑bench without affecting the underlying agent.
By Jizhe Zhang, Ang Li, Chenheng Zhang, Yisen Wang
arXiv:2610.29866v1 Announce Type: new
Abstract: Geometric structure is essential for robotic manipulation and understanding the 3D world. Most VLA models rely on 2D representations of current observa...
By Qinfan Zhang, Yifan Luo, Haoyuan Shi, Guanlin Liu, Han Dong, Haozhe Shan, Yong Dai, Xiangcong Ren, Xiaozhu Ju
Geometric structure is essential for robotic manipulation and understanding the 3D world. Most VLA models rely on 2D representations of current observations, while geometry-aware approaches often requ...
Long‑horizon language model agents accumulate reasoning history, which inflates context length and inference cost. The paper introduces Interaction Aware Compression for Long Horizon Reasoning (ICLR), a training‑free online method that ranks and removes reasoning blocks based on frozen proxy entropy while preserving actions, tool calls, and observations. On 260 WorkBuddyBench tasks, ICLR raises average reward from 0.699 to 0.718 and cuts input, output, and cache read tokens by 25.5%, 14.4%, and 33.3% respectively, while analyses show that historical reasoning becomes replaceable once task‑relevant state is externalized.
By Mingxuan Wang, Fei Luo, Bo Wang, Guorun Yao, Yinglong Guo, Chao Ning, Hongyue Chen, Yanbiao Ma, Jungong Han