arXiv AI July 28, 2026 By Chengzhang Yu, Chenyang Zheng, Zening Lu, Yingru He, Yutong Huang, Yiming Zhang, Yue Xu, Zhanpeng Jin

TokenMem: Faithful Knowledge Injection for Frozen LLMs

Read the original on arXiv AI →

arXiv:2607. 22625v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge, but suffers from knowledge conflicts: when retrieved information contradicts parametric memory, the shared self-attention pathway produces unpredictable outputs.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

1d ago

Cross-Model Memory Transfer via Target-Side Reader Adaptation

arXiv:2608. 17050v1 Announce Type: cross Abstract: Methods for improving knowledge use in large language models typically fall into two regimes.

By Mingyuan Li, Guangsheng Yu, Xu Wang, Shaoxiong Ji

llms nlp safety

arXiv AI

Aug 5

Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents

arXiv:2608. 03137v1 Announce Type: new Abstract: Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon interaction.

By Xiaolong Sun, Qichao Wang, Hangyu Li, Liang Chen

llms agents fine-tuning benchmarks

arXiv AI

Jun 29

SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation

arXiv:2606. 27786v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) enhances LLMs by incorporating external knowledge to support response generation.

By Ruochang Li, Pengcheng Huang, Zhenghao Liu, Yukun Yan, Huiyuan Xie, Yu Gu, Ge Yu, Maosong Sun

llms rag

arXiv AI

Jul 24

CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents

arXiv:2607. 20458v1 Announce Type: cross Abstract: Large language model (LLM) agents operating over extended dialogues accumulate vast amounts of information, yet existing memory systems either retain everything indiscriminately or apply uniform forgetting heuristics that fail to distinguish relevant from irrelevant knowledge.

By Haowen Lai

llms rag agents benchmarks

arXiv AI

Jul 3

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

arXiv:2607. 02010v1 Announce Type: new Abstract: Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time.

By Qianyu Chen, Ziteng Feng, Canran Xiao, Runxuan Tang

llms fine-tuning multimodal

arXiv AI

Jul 3

Procedural Memory Distillation: Online Reflection for Self-Improving Language Models

arXiv:2607. 01480v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifier and updates the policy from that episode-level signal.

By Ye Liu, Srijan Bansal, Bo Pang, Yang Li, Zeyu Leo Liu, Yifei Ming, Zixuan Ke, Shafiq Joty, Semih Yavuz

llms reinforcement-learning efficiency

Related stories

Cross-Model Memory Transfer via Target-Side Reader Adaptation

Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents

SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation

CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

Procedural Memory Distillation: Online Reflection for Self-Improving Language Models