Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation

• URL: http://arxiv.org/abs/2502.12492v1
• Date: Tue, 18 Feb 2025 03:20:50 GMT
• Title: Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation
• Authors: Kounianhua Du, Hanjing Wang, Jianxing Liu, Jizheng Chen, Xinyi Dai, Yasheng Wang, Ruiming Tang, Yong Yu, Jun Wang, Weinan Zhang,
• Abstract summary: Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks.<n>Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation.<n>In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges.
• Score: 58.799397354312596
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks, yet the intricacies of their problem-solving mechanisms in system 2 tasks are not sufficiently explored. Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation and compressing the explored knowledge into System 1 process. In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges: (1) the complex hidden reasoning processes and (2) the heterogeneous data distributions that complicate the exploration and training of robust LLM solvers. To tackle these issues, we propose a novel BDC framework that explores insightful System 2 knowledge of LLMs using a MC-Tree-Of-Agents algorithm with mutual \textbf{B}oosting, \textbf{D}isentangles the heterogeneous training data for composable LoRA-experts, and obtain \textbf{C}ustomized problem solver for each data instance with an input-aware hypernetwork to weight over the LoRA-experts, offering effectiveness, flexibility, and robustness. This framework leverages multiple LLMs through mutual verification and boosting, integrated into a Monte-Carlo Tree Search process enhanced by reflection-based pruning and refinement. Additionally, we introduce the DisenLora algorithm, which clusters heterogeneous data to fine-tune LLMs into composable Lora experts, enabling the adaptive generation of customized problem solvers through an input-aware hypernetwork. This work lays the groundwork for advancing LLM capabilities in complex reasoning tasks, offering a novel System2-to-System1 solution.

Related papers

• A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems [93.8285345915925]
  Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making. With the rapid advancement of large language models (LLMs), reasoning has emerged as a key capability that distinguishes advanced AI systems. We categorize existing methods along two dimensions: (1) Regimes, which define the stage at which reasoning is achieved; and (2) Architectures, which determine the components involved in the reasoning process.
  arXiv  Detail & Related papers  (2025-04-12T01:27:49Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models. Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start. Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• Trustworthy Answers, Messier Data: Bridging the Gap in Low-Resource Retrieval-Augmented Generation for Domain Expert Systems [7.76315323320043]
  We introduce a data generation pipeline that transforms raw multi-modal data into structured corpus and Q&A pairs. Our system improves factual correctness (+1.94), informativeness (+1.16), and helpfulness (+1.67) over a non-RAG baseline. Results highlight the effectiveness of our approach across distinct aspects, with strong answer grounding and transparency.
  arXiv  Detail & Related papers  (2025-02-26T22:20:08Z)
• mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA [78.45521005703958]
  multimodal Retrieval-Augmented Generation (mRAG) is naturally introduced to provide MLLMs with comprehensive and up-to-date knowledge. We propose a novel framework called textbfRetrieval-textbfReftextbfAugmented textbfGeneration (mR$2$AG) which achieves adaptive retrieval and useful information localization. mR$2$AG significantly outperforms state-of-the-art MLLMs on INFOSEEK and Encyclopedic-VQA
  arXiv  Detail & Related papers  (2024-11-22T16:15:50Z)
• Visual Reasoning and Multi-Agent Approach in Multimodal Large Language Models (MLLMs): Solving TSP and mTSP Combinatorial Challenges [5.934258790280767]
  Multimodal Large Language Models (MLLMs) harness comprehensive knowledge spanning text, images, and audio to adeptly tackle complex problems. This study explores the ability of MLLMs in visually solving the Traveling Salesman Problem (TSP) and Multiple Traveling Salesman Problem (mTSP) We introduce a novel approach employing multiple specialized agents within the MLLM framework, each dedicated to optimizing solutions for these challenges.
  arXiv  Detail & Related papers  (2024-06-26T07:12:06Z)
• Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding [27.004817441034795]
  Collaborative decoding between large and small language models (SLMs) presents a promising strategy to mitigate these issues. Inspired by dual-process cognitive theory, we propose a unified framework, termed Fast and Slow Generating (FS-GEN) Within this framework, LLMs are categorized as System 2 (slow and deliberate), while independent SLMs are designated as System 1.
  arXiv  Detail & Related papers  (2024-06-18T05:59:28Z)
• Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
  Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
  arXiv  Detail & Related papers  (2024-03-12T13:31:14Z)
• Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions [47.83142414018448]
  We focus on two popular reasoning tasks: arithmetic reasoning and code generation. We introduce (i) a general ontology of perturbations for math and coding questions, (ii) a semi-automatic method to apply these perturbations, and (iii) two datasets. We show a significant performance drop across all the models against perturbed questions.
  arXiv  Detail & Related papers  (2024-01-17T18:13:07Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• A Hierarchical Approach to Conditional Random Fields for System Anomaly Detection [0.8164433158925593]
  Anomaly detection to recognize unusual events in large scale systems is critical in many industries. A hierarchical approach takes advantage of the implicit relationships in complex systems and localized context.
  arXiv  Detail & Related papers  (2022-10-26T21:02:47Z)

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.