PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding

[2506.17310] PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Quantitative Biology > Neurons and Cognition arXiv:2506.17310 (q-bio) [Submitted on 18 Jun 2025 ( v1 ), last revised 10 Apr 2026 (this version, v3)] Title: PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding Authors: Kangcong Li , Peng Ye , Chongjun Tu , Lin Zhang , Chunfeng Song , Jiamin Wu , Tao Yang , Qihao Zheng , Tao Chen View a PDF of the paper titled PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding, by Kangcong Li and 8 other authors View PDF HTML (experimental) Abstract: While Large Language Models (LLMs) demonstrate strong performance across domains, their long-context capabilities are limited by transient neural activations causing information decay and unstructured feed-forward network (FFN) weights leading to semantic fragmentation. Inspired by the brain's working memory and cortical modularity, we propose PaceLLM, featuring two innovations: (1) a Persistent Activity (PA) Mechanism that mimics prefrontal cortex (PFC) neurons' persistent firing by introducing an activation-level memory bank to dynamically retrieve, reuse, and update critical FFN states, addressing contextual decay; and (2) Cortical Expert (CE) Clustering that emulates task-adaptive neural specialization to reorganize FFN weights into semantic modules, establishing cross-token dependencies and mitigating fragmentation. Extensive evaluations show that PaceLLM achieves 6% improvement on LongBench's Multi-document QA and 12.5-17.5% performance gains on Infinite-Bench tasks, while extending measurable context length to 200K tokens in Needle-In-A-Haystack (NIAH) tests. This work pioneers brain-inspired LLM optimization and is complementary to other works. Besides, it can be generalized to any model and enhance their long-context performance and interpretability without structural overhauls. Comments: Accepted by NeurIPS 2025 Subjects: Neurons and Cognition (q-bio.NC) ; Computation and Language (cs.CL); Neural and Evolutionary Computing (cs.NE) Cite as: arXiv:2506.17310 [q-bio.NC] (or arXiv:2506.17310v3 [q-bio.NC] for this version) https://doi.org/10.48550/arXiv.2506.17310 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Kangcong Li [ view email ] [v1] Wed, 18 Jun 2025 09:17:06 UTC (1,275 KB) [v2] Mon, 2 Feb 2026 06:05:34 UTC (1,267 KB) [v3] Fri, 10 Apr 2026 08:34:15 UTC (1,267 KB) Full-text links: Access Paper: View a PDF of the paper titled PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding, by Kangcong Li and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: q-bio.NC < prev | next > new | recent | 2025-06 Change to browse by: cs cs.CL cs.NE q-bio References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Neural Language Models’ sensitivity to long-distance dependencies and their island constraints is not universal: a comparison between English and Dutch humans and models#331597
• Large Language Models Can Be Easily Distracted by Irrelevant Context#16606
• Folk psychological attributions of consciousness to large language models#328729
• Emergent Sensorimotor Representation in Large Language Models: Revisiting Human-machine Alignment on Sensorimotor Intuitions of Concepts#387686
• Temporal Tree of Thought: Reasoning-Guided Visual Cue Search for Long-Video Understanding#781156