MapCoder-Lite: Squeezing Multi-Agent Coding into a Single Small LLM

• URL: http://arxiv.org/abs/2509.17489v1
• Date: Mon, 22 Sep 2025 08:19:11 GMT
• Title: MapCoder-Lite: Squeezing Multi-Agent Coding into a Single Small LLM
• Abstract summary: MapCoder-Lite upgrades a single 7B model into four role-specialised agents-retriever, planner, coder, and debugger-using only rank-32.<n>MapCoder-Lite more than doubles xCodeEval accuracy (from $13.2%$ to $28.3%$), eliminates all format failures, and closes to within six points of a 32B baseline.
• Score: 9.44363104217319
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale ($>$ 30B) models or collapse when downsized to small open-source models. We present MapCoder-Lite, which upgrades a single 7B model into four role-specialised agents-retriever, planner, coder, and debugger-using only rank-32, role-specific LoRA adapters ($<3\%$ extra parameters). Three lightweight techniques make this possible: (i) trajectory distillation from strong LLMs fixes format fragility in retrieval and debugging, (ii) supervisor-guided correction strengthens planning and coding agents, and (iii) agent-wise LoRA fine-tuning delivers memory-efficient specialisation. Comprehensive evaluation on xCodeEval, APPS, and CodeContests shows that MapCoder-Lite more than doubles xCodeEval accuracy (from $13.2\%$ to $28.3\%$), eliminates all format failures, and closes to within six points of a 32B baseline while cutting GPU memory and token-generation time by $4\times$. These results demonstrate that careful agent-wise fine-tuning unleashes high-quality multi-agent coding on a small language model.

Related papers

• Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems [67.04448659688579]
  We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
  arXiv  Detail & Related papers  (2026-09-02T08:10:22Z)
• MARS: Multi-Specialist LLM Relay System for Competitive Programming [3.8421682531018564]
  MARS (Multi-Agent Relay of Specialized LLMs) is a prompt-only framework in which each agent is a topic specialist.<n>A starter writes an initial C++17 solution, and each subsequent turn runs the candidate against public examples in a sandbox.<n>A single infrastructure-fixer pass normalizes boilerplate at the end.
  arXiv  Detail & Related papers  (2026-08-24T23:51:02Z)
• Functional and Secure Code Generation with Task Vectors [7.757776817999749]
  Large language models (LLMs) are increasingly used for code generation, but they struggle to generate functional code free of security vulnerabilities.<n>We develop a novel method, SecVecCoder, leveraging task vectors to produce trustworthy code that is simultaneously functional and secure.
  arXiv  Detail & Related papers  (2026-07-08T19:32:22Z)
• BLAgent: Agentic RAG for File-Level Bug Localization [2.2917707112773593]
  BLAgent is a novel agentic RAG framework for file-level bug localization.<n> BLAgent attains over 78% Top-1 accuracy with open-source models.<n> BLAgent improves end-to-end repair success by over 20%.
  arXiv  Detail & Related papers  (2026-05-18T07:20:13Z)
• Resource-Efficient Iterative LLM-Based NAS with Feedback Memory [49.44875022114861]
  Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources.<n>We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures.
  arXiv  Detail & Related papers  (2026-03-12T16:00:22Z)
• One LLM to Train Them All: Multi-Task Learning Framework for Fact-Checking [7.856998585396422]
  Large language models (LLMs) are reshaping automated fact-checking (AFC) by enabling unified, end-to-end verification pipelines.<n>We propose textbfmulti-task learning (MTL) as a more efficient alternative that fine-tunes a single model to perform claim detection, evidence ranking, and stance detection jointly.
  arXiv  Detail & Related papers  (2026-01-16T13:44:25Z)
• VisCoder2: Building Multi-Language Visualization Coding Agents [63.63232038173407]
  We introduce three complementary resources for advancing visualization coding agents.<n>VisCoder2 significantly outperforms strong open-source baselines and approaches the performance of proprietary models.
  arXiv  Detail & Related papers  (2025-10-24T18:03:57Z)
• Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs [0.10742675209112619]
  Small language models (SLMs; 1-12B params, sometimes up to 20B) are sufficient and often superior for agentic workloads.<n>We synthesize recent evidence across open and proprietary SLMs and connect it to modern evaluations.<n>We formalize SLM-fallback systems with uncertainty-aware routing and verifier cascades, and propose engineering metrics that reflect real production goals.
  arXiv  Detail & Related papers  (2025-10-04T15:48:04Z)
• Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights [75.83625828306839]
  textbfDrag-and-Drop LLMs (textitDnD) eliminates per-task training by mapping a handful of unlabeled task prompts directly to LoRA weight updates.<n>A lightweight text encoder distills each prompt batch into condition embeddings, which are then transformed by a cascaded hyper-convolutional decoder into the full set of LoRA matrices.
  arXiv  Detail & Related papers  (2025-06-19T15:38:21Z)
• AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation [17.020112052995334]
  A typical multi-agent framework consists of Large Language Model (LLM)-based agents.<n>AdaCoder is a novel adaptive planning, multi-agent framework for function-level code generation.
  arXiv  Detail & Related papers  (2025-04-05T16:14:01Z)
• Quantizing Large Language Models for Code Generation: A Differentiated Replication [51.85505914274633]
  Large Language Models (LLMs) have shown an impressive capability in code generation and, specifically, to automatically implement requirements described in natural language.<n>LLMs pose significant challenges related to their memory (and, consequently, carbon) footprint.<n>New frontier for LLM quantization is 4-bit precision, resulting in an average memory footprint reduction of 70%.
  arXiv  Detail & Related papers  (2025-03-10T09:26:08Z)
• CodeLutra: Boosting LLM Code Generation via Preference-Guided Refinement [32.46078765471136]
  Large Language Models (LLMs) have revolutionized code generation but require significant resources and often over-generalize.<n>We introduce CodeLutra, a framework that leverages both correct and incorrect code attempts.<n>By learning from both successes and mistakes, CodeLutra provides a scalable and efficient path to high-quality code generation.
  arXiv  Detail & Related papers  (2024-11-07T21:51:07Z)
• Are Decoder-Only Large Language Models the Silver Bullet for Code Search? [44.9422305001193]
  Code search is essential for code reuse, allowing developers to efficiently locate relevant code snippets.<n>Powerful decoder-only Large Language Models (LLMs) has revolutionized many code intelligence tasks.<n>This paper presents a systematic evaluation of eleven decoder-only LLMs, analyzing their performance across zero-shot and fine-tuned settings.
  arXiv  Detail & Related papers  (2024-10-29T17:05:25Z)
• SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer [0.0]
  SuperCoder2.0 is an advanced autonomous system designed to enhance software development through artificial intelligence. System combines an AI-native development approach with intelligent agents to enable fully autonomous coding.
  arXiv  Detail & Related papers  (2024-09-17T13:44:42Z)
• Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector [114.88975874411142]
  Hallucination detection is a challenging task for large language models (LLMs) We propose an autonomous LLM-based agent framework, called HaluAgent. In HaluAgent, we integrate the LLM, multi-functional toolbox, and design a fine-grained three-stage detection framework.
  arXiv  Detail & Related papers  (2024-06-17T07:30:05Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)
• CodeT5+: Open Code Large Language Models for Code Understanding and Generation [72.1638273937025]
  Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. CodeT5+ is a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks. We extensively evaluate CodeT5+ on over 20 code-related benchmarks in different settings, including zero-shot, finetuning, and instruction-tuning.
  arXiv  Detail & Related papers  (2023-05-13T14:23:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.