SEMAG: Self-Evolutionary Multi-Agent Code Generation

• URL: http://arxiv.org/abs/2603.15707v1
• Date: Mon, 16 Mar 2026 13:24:55 GMT
• Title: SEMAG: Self-Evolutionary Multi-Agent Code Generation
• Abstract summary: We propose SEMAG, a Self-Evolutionary Multi-Agent code Generation framework that mimics human coding practices.<n>It decomposes programming tasks into stages, including planning, coding, debug and discussion, while adapting to task difficulty.<n>Using identical backbone models, SEMAG outperforms prior methods by 3.3% on CodeContests.
• Score: 42.05124551923306
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have made significant progress in handling complex programming tasks. However, current methods rely on manual model selection and fixed workflows, which limit their ability to adapt to changing task complexities. To address this, we propose SEMAG, a Self-Evolutionary Multi-Agent code Generation framework that mimics human coding practices. It decomposes programming tasks into stages, including planning, coding, debugging, and discussion, while adapting workflows to task difficulty. Its self-evolutionary agents can access the latest models in real time and automatically upgrade the backbone model. SEMAG sets new state-of-the-art Pass@1 accuracy across benchmarks. Using identical backbone models, SEMAG outperforms prior methods by 3.3% on CodeContests. When augmented with self-evolutionary model selection that automatically identifies optimal backbones, SEMAG reaches 52.6%, showcasing both framework effectiveness and adaptability to evolving LLM capabilities.

Related papers

• Self-Evolving Embodied Agents via Skill-Harness Evolution [53.307052568223945]
  Embodied agents are increasingly built as systems around foundation models.<n>While supervised fine-tuning and reinforcement learning can adapt agents to new environments, they require additional data, rewards, and training runs.<n>We propose SHAPER, a self-evolving framework for train-free embodied adaptation that keeps model parameters frozen.
  arXiv  Detail & Related papers  (2026-08-11T18:55:58Z)
• MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction [18.226927359110018]
  We introduce MM-ReCoder, a chart-to-code generation model trained with reinforcement learning (RL)<n>We propose a two-stage multi-turn self-correction RL strategy based on Group Relative Policy Optimization (GRPO)<n>Our results on three chart-to-code benchmarks demonstrate the state-of-the-art performance of MM-ReCoder.
  arXiv  Detail & Related papers  (2026-04-02T04:21:09Z)
• Evolutionary Generation of Multi-Agent Systems [49.47969796873096]
  Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks.<n>EvoMAS formulates MAS generation as structured configuration generation.<n>EvoMAS consistently improves task performance over both human-designed MAS and prior automatic MAS generation methods.
  arXiv  Detail & Related papers  (2026-02-06T09:01:35Z)
• Reinforced Language Models for Sequential Decision Making [6.971286730860635]
  Large Language Models (LLMs) show potential as sequential decision-making agents.<n>Existing post-training methods are designed for single-turn interactions and cannot handle credit assignment in multi-step agentic tasks.<n>This work demonstrates that targeted post-training is a practical and efficient alternative to relying on model scale for creating sequential decision-making agents.
  arXiv  Detail & Related papers  (2025-08-14T17:05:44Z)
• Self-Adapting Language Models [47.52508465862889]
  Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples.<n>We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by generating their own finetuning data and update directives.<n> Experiments on knowledge incorporation and few-shot generalization show that SEAL is a promising step toward language models capable of self-directed adaptation.
  arXiv  Detail & Related papers  (2025-06-12T17:48:13Z)
• OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging [124.91183814854126]
  Model merging seeks to combine multiple expert models into a single model.<n>We introduce a benchmark for model merging research that clearly divides the tasks for MLLM training and evaluation.<n>We find that model merging offers a promising way for building improved MLLMs without requiring training data.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• SEW: Self-Evolving Agentic Workflows for Automated Code Generation [24.16770109875788]
  We propose textbfSelf-textbfEvolving textbfWork (textbfSEW), a novel framework that automatically generates and optimises multi-agentflow.<n>Our SEW can automatically design agentic and optimise them through self-evolution, bringing up to 33% improvement on LiveCodeBench.
  arXiv  Detail & Related papers  (2025-05-24T11:12:14Z)
• Model Evolution Framework with Genetic Algorithm for Multi-Task Reinforcement Learning [85.91908329457081]
  Multi-task reinforcement learning employs a single policy to complete various tasks, aiming to develop an agent with generalizability across different scenarios.<n>Existing approaches typically use a routing network to generate specific routes for each task and reconstruct a set of modules into diverse models to complete multiple tasks simultaneously.<n>We propose a Model Evolution framework with Genetic Algorithm (MEGA), which enables the model to evolve during training according to the difficulty of the tasks.
  arXiv  Detail & Related papers  (2025-02-19T09:22:34Z)
• MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration [11.01813164951313]
  This paper introduces MorphAgent, a novel Autonomous, Self-Organizing, and Self-Adaptive Multi-Agent System.<n>Our approach employs self-evolving agent profiles, optimized through three key metrics, guiding agents in refining their individual expertise.<n>Our experimental results show that MorphAgent outperforms existing frameworks in terms of task performance and adaptability to changing requirements.
  arXiv  Detail & Related papers  (2024-10-19T09:10:49Z)
• MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval [4.4173427917548524]
  MultiWay-Adapter (MWA) is a novel framework featuring an 'Alignment Enhancer' This enhancer deepens inter-modal alignment, enabling high transferability with minimal tuning effort. Experiments show that unlike prior efficient tuning approaches, MWA maintains model effectiveness, while reducing training time by up-to 57%.
  arXiv  Detail & Related papers  (2023-09-04T10:48:29Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Improving Non-autoregressive Generation with Mixup Training [51.61038444990301]
  We present a non-autoregressive generation model based on pre-trained transformer models. We propose a simple and effective iterative training method called MIx Source and pseudo Target. Our experiments on three generation benchmarks including question generation, summarization and paraphrase generation, show that the proposed framework achieves the new state-of-the-art results.
  arXiv  Detail & Related papers  (2021-10-21T13:04:21Z)

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.