The paper introduces READ, a method for composing low‑rank adapters (LoRA) in large language models. By rewriting each adapter into a balanced canonical form and enforcing a one‑directional coupling, READ allows new skills to read but never write into the output subspaces of existing skills, eliminating interference. Experiments on four benchmark suites and two model families show that READ consistently outperforms existing baselines, improving SuperGLUE scores by over twenty points and domain suite scores by more than seven points.
By Zeyan Li, Panqi Yang, Qirong Guo, Shengda Zhuo, SIyuan Qiu, Hu Xu, Chun Li, Jianfeng Xu
arXiv:2602. 05988v2 Announce Type: replace Abstract: Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI.
By Keith Ando Ogawa, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Lucas Pellicer, Rosimeire Pereira Costa, Edson Bollis, Anna Helena Reali Costa, Artur Jordao
arXiv:2607. 20438v1 Announce Type: cross Abstract: Preference-based post-training is usually understood through endpoint behavior, yet the learned update that produces this behavior remains largely opaque.
By Peiyan Zhang, Haibo Jin, Liying Kang, Haohan Wang
arXiv:2605.07111v3 Announce Type: replace-cross
Abstract: Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides greater represe...
By Haozhan Tang, Xiuqi Zhu, Xinyin Zhang, Boxun Li, Virginia Smith, Kevin Kuo
The paper introduces ISO-LoRA, an optimizer that improves rank utilization in Low‑Rank Adaptation (LoRA) by coupling factor updates through spectral descent on the induced tangent perturbation in weight space. Experiments on GPT‑2 adaptation show that standard optimizers like AdamW concentrate updates in a few singular directions, whereas ISO-LoRA distributes energy more evenly, leading to higher effective rank and better downstream performance across 0.1B‑7B models. The authors provide theoretical guarantees under a stylized spiked‑gradient model and demonstrate that ISO-LoRA consistently outperforms factor‑wise optimizers, especially at moderate‑to‑large LoRA ranks.
By Zihan Zhu, Zhehang Du, Xuyang Chen, Tim Tsz-Kit Lau, Jiayuan Wu, X. Y. Han, Qi Long, Weijie Su
arXiv:2606. 04536v1 Announce Type: new Abstract: Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model parameters frozen throughout a rollout.
By Tao Ren, Weiyao Luo, Hui Yang, Rongzhi Zhu, Xiang Huang, Yuchuan Wu, Bingxue Chou, Jieping Ye, Jiafeng Liang, Yongbin Li, Yijie Peng
arXiv:2607. 16637v1 Announce Type: new Abstract: Full fine-tuning remains a strong way to adapt pretrained LLMs, but it updates all weights and can be expensive.
By Abdulkadir Erol, Yash Mahajan, Vepaul Hariprashad, Baha Rababah, Santu Karmaker, Cuneyt G. Akcora, Mubarak Shah
arXiv:2606. 28117v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become the standard tool for parameter-efficient fine-tuning of large pretrained models.
By Tanguy Dieudonn\'e, Giulia Lanzillotta, Enis Simsar, Louis Barinka, Thomas Hofmann
The paper introduces BQ-LoRA, a low‑rank adaptation framework for large language model agents that consolidates multiple LoRA adapters into a single one. It uses a behavior quotient manifold to balance trajectory updates and a decision‑preserving compression module to keep updates within a fixed rank budget while minimizing distortion of decision distributions. Experiments on AppWorld and BrowseComp‑Plus demonstrate that BQ‑LoRA outperforms standard LoRA and other low‑rank methods, with ablations confirming the benefits of both components.
By Pengyang Zhou, Xiaobin Tu, Zhengxi Liu, Rongkun Xue, Haochen Li, Miancan Liu, Ziyuan Chen, Yinggui Wang, Jinkui Ren, Xiantao Zhang
arXiv:2607. 22251v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for large language models, but its performance depends strongly on how a fixed rank budget is distributed across Transformer modules.
By Wei Zhang, Xinwu Liu, Yihang Cheng
arXiv:2608. 10333v1 Announce Type: new Abstract: LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or tool-argument construction.
By Yuhang Yao, Zeyu Wang, Wanyi Chen, Tongyun Yang, Yuhang Han, Jie Xiao, Chengke Bao, Tianyi Zhao, Lynn Ai, Eric Yang, Tianyu Shi
The paper introduces CLAW, a method that uses a hypernetwork to generate low‑rank adapters for world models during test time, enabling efficient adaptation to new environments with only a few episodes of interaction. By jointly pretraining the hypernetwork and base model on simulated adaptations, CLAW balances computational efficiency and expressivity, outperforming both in‑context learning and gradient‑based adaptation in locomotion and manipulation tasks. The approach also mitigates overfitting in data‑scarce regimes and demonstrates that the benefit stems from expressive adapters rather than context conditioning.
By Fernando Palafox, David Fridovich-Keil