Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase
Summary
The Super Library Agent framework reduces redundancy and structural erosion in LLM-driven code generation by introducing a shared-library approach for maintaining multiple related applications.
View Cached Full Text
Cached at: 09/01/26, 11:43 AM
Paper page - Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase
Source: https://huggingface.co/papers/2608.29310
Abstract
A shared-library agent framework reduces redundancy and structural erosion when sequentially generating related applications by guiding cross-application code extraction and migration.
Organizations often develop and maintain portfolios of related applications: independently deployable codebases that share substantial domain logic, interface patterns, or operational conventions. As LLM coding agents are increasingly used to generate and maintain such software, a naive application-by-application workflow duplicates shared logic across codebases and allows prolonged agentic maintenance to accumulate verbosity, dead code, and structural erosion. We introduce theSuper Library Agentproblem, where an agent sequentially generates a portfolio of N related applications while maintaining a shared Super Library of reusable cross-application components. A minimal sequential scaffold can in principle extract shared code and migrate applications to the evolving library, but in practice suffers from low extraction recall and fragile dependency migration. We address these failures withcandidate-guided extractionovercode chunk summaries, pre-extraction codebase consolidation, andcontext-aware migrationusingextraction tracesandcall-graphinformation. AcrossWebGen-BenchandPaperBench, our method preserves application functionality while significantly reducing redundancy and token footprint (verbosity, token length) over zero-shot, and avoiding the structural erosion introduced by naive library construction, with additional reductions in LOC and MDL. Our code is available at https://github.com/sbigstar0310/super-library-agent.
View arXiv pageView PDFProject pageGitHub0Add to collection
Get this paper in your agent:
hf papers read 2608\.29310
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.29310 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.29310 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.29310 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Can Agents Design Libraries for Agents?
The paper introduces LibraryDesignBench, a two-phase benchmark that has one AI agent write software libraries from underspecified requirements, then scores each library by how effectively other agent implementers use it to solve programming problems in minimal code. The evaluation metric combines squared pass rate with solution simplicity relative to a production-library reference.
Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents
Agent libOS introduces a library-OS-inspired runtime substrate for LLM agents, treating agents as schedulable processes with explicit capabilities, lifecycle management, audit records, and human approval queues. The design shifts the trust boundary from tool dispatch to runtime primitives, enabling long-running agents to be scheduled, authorized, resumed, and audited safely.
We built a source-available LLM reliability library (free for research / personal / internal eval) that can cut inference cost by half at matched quality, and you adopt it by changing one import [P] [R]
AgentCodec is a source-available library unifying 28 LLM reliability techniques (retries, ensembling, generator/critic refinement, etc.) under a single OpenAI-compatible API, with adaptive routers that can reduce inference costs by ~56% at matched quality. It adopts a communication-theory framing and supports drop-in replacement for OpenAI, Anthropic, and Ollama clients.
@gneubig: We've found this sort of "sidekick" architecture to be very effective at cutting LLM spend because it allows you to do …
Graham Neubig shares a sidekick architecture for reducing LLM costs by delegating simple tasks to a smaller agent, with a 200-line example using the OpenHands SDK. This approach is also used in Cognition's Devin Fusion hybrid-model harness.
Rethinking Multi-Agent Collaboration: When More Is Less
This paper delineates the capability boundaries of multi-agent collaboration in LLM-based systems, showing benefits only in specific task structures like long-horizon tasks with sparse dependencies, and proposes SAIGE, a dynamic graph-based mechanism for efficient collaboration.