arXiv AI October 1, 2026 By Ubaidillah Ariq Prathama, Bo Liu, Yeo Boon Hong, Yu-Xuan Huang, Yangkai Ding, Tao Yu

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

RefCon is a method for extracting higher‑quality memories in context‑evolving agents by combining sequential self‑refinement with parallel self‑contrast, without relying on gold labels. It shows strong, consistent gains on benchmarks such as AppWorld, BFCL‑V3, ACE, ReMe, and ReasoningBank, outperforming existing baselines across different model scales and even surpassing ground‑truth baselines in software engineering tasks. The approach also maintains favorable efficiency and continues to improve as more trajectories are used, unlike diversity‑only scaling which saturates earlier.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

agents

arXiv AI

Jul 21

Mechanistic Attention Guidance for Agent Memory Refinement

arXiv:2607. 17621v1 Announce Type: new Abstract: Existing self-evolving memory systems mainly improve agent memory based on textual outputs, such as task trajectories and reflections.

By Yechao Hong, Haiquan Qiu, Yaqing Wang, Quanming Yao

agents benchmarks

arXiv AI

Oct 9

REMORY: Learning Residual Memory for Context Compaction

REMORY is a neural memory network that augments a textual summary of an agent’s history with a small set of soft memory tokens. These tokens, conditioned on the summary, enable a frozen large language model to approximate the continuation it would generate using the full history, effectively acting as a residual connection along the sequence dimension. Experiments on SummHay and long‑horizon agent benchmarks show that REMORY improves source attribution, maintains insight coverage, and achieves near full‑context performance while using only 5.2% of the input positions, while also reducing repeated tool outputs and errors on BrowseComp and Terminal‑Bench 2.1.

By Hanchen Xia, Baoyou Chen, Yutang Ge, Naihao Deng, Senqiao Yang, Zilong Dong, Weihao Yuan, Siyu Zhu

llms agents benchmarks

arXiv AI

Jun 16

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.

By Yuyao Wang, Zhongjian Zhang, Mo Chi, Kaichi Yu, Yuhan Li, Miao Peng, Bing Tong, Chen Zhang, Yan Zhou, Jia Li

llms agents benchmarks

arXiv AI

Jul 16

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

arXiv:2607. 13591v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.

By Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu, Levina Li, Dong Liu, Xiao Liang, Rui Sun, Yubei Li, Edward Sun, Haozheng Luo, Zhaolu Kang, Aylin Caliskan, Kai-Wei Chang, Ying Nian Wu

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 6

Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents

arXiv:2606. 06036v1 Announce Type: new Abstract: Despite recent progress, LLM agents still struggle with reasoning over long interaction histories.

By Shuo Ji, Yibo Li, Bryan Hooi

llms agents benchmarks

arXiv AI

Jun 24

ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling

arXiv:2606. 24437v1 Announce Type: new Abstract: Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines.

By Heng Ping, Arijit Bhattacharjee, Peiyu Zhang, Shixuan Li, Wei Yang, Ali Jannesari, Nesreen Ahmed, Paul Bogdan

llms agents efficiency benchmarks

One email a morning, machine-written

Related stories

Mechanistic Attention Guidance for Agent Memory Refinement

REMORY: Learning Residual Memory for Context Compaction

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents

ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling