ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits

[2608.15138] ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.15138 (cs) [Submitted on 15 Aug 2026] Title: ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits Authors: Zhiqiang He , Zhi Liu View a PDF of the paper titled ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits, by Zhiqiang He and Zhi Liu View PDF HTML (experimental) Abstract: Designing an ABR algorithm for one network scenario takes an engineer months, and large language models now do this work in hours, matching or beating hand-built designs. But either way, the design fits only the world visible at its birth, and fails on the world that arrives after. We ask whether an ABR algorithm can keep pace with the world, redesigned in minutes as each scenario arrives, with every change proven harmless to every scenario already served. In this work, we propose ReForge, a continual heuristic learning framework that adapts to continuously changing scenarios. ReForge runs that routine with a large language model (LLM) in the loop. Each round the LLM reads where the current design falls short and proposes one small edit, and a replay over every network served so far decides. Specifically, what it edits is a single page of fuzzy rules that routes every decision to one of a frozen pool of pre-trained policies. The LLM writes the first page from measurements alone, then keeps improving it on its own. Each round it reads where the current rules fall short and proposes one small edit, and a replay over every network served so far decides whether the edit lands. We evaluate ReForge on nine real-world network families arriving one at a time as 3G, 4G, then 5G. A few edits per arrival lift mean QoE from 1.23 to 1.74, past the best single policy at 1.66 and to 94\% of an oracle, and even repair families the loop never saw, one rising from 0.30 to 0.80. All code, data, and experiment records will be open-sourced upon cleanup. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2608.15138 [cs.AI] (or arXiv:2608.15138v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.15138 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhiqiang He [ view email ] [v1] Sat, 15 Aug 2026 09:23:24 UTC (614 KB) Full-text links: Access Paper: View a PDF of the paper titled ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits, by Zhiqiang He and Zhi Liu View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs 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

• ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits#611087
• Learning to Solve Hard Problems in RL for LLMs by Never Giving Up#1071231
• Collaborative Large and Small Language Models for Accurate and Scalable Data Repair#282893
• An Empirical Study on the Potential of LLMs in Automated Software Refactoring#1037683
• Exploring Causal Mechanisms with Generative Agent-Based Models#1130661