Compressing Code Context for LLM-based Issue Resolution

• URL: http://arxiv.org/abs/2603.28119v1
• Date: Mon, 30 Mar 2026 07:31:12 GMT
• Title: Compressing Code Context for LLM-based Issue Resolution
• Abstract summary: Large Language Models (LLMs) are now capable of resolving real-world GitHub issues.<n>Existing compression techniques fail to resolve this tension.<n>We propose a novel framework consisting of two components.
• Score: 6.6121784437529
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are now capable of resolving real-world GitHub issues. However, current approaches overapproximate the code context and suffer from two compounding problems: the prohibitive cost of processing massive inputs, and low effectiveness as noise floods the context window and distracts the model from the bug-fixing signal. Existing compression techniques fail to resolve this tension: generic compressors compromise the semantic integrity of code, while code-specific tools lack awareness of code structure and task context to preserve essential patch ingredients. To address this, we propose a novel framework consisting of two components. First, Oracle-guided Code Distillation (OCD), a context distillation algorithm that combines genetic search and delta debugging to systematically reduce code contexts to their minimal sufficient subsequence - retaining only the ingredients required for a successful fix. We use this distilled data to fine-tune SWEzze, a lightweight model that learns to compress code context at inference time, filtering noise and combating distraction while preserving fix ingredients. Evaluated on SWE-bench Verified across three frontier LLMs, SWEzze maintains a stable compression rate of about 6 times across models, reduces the total token budget by 51.8%-71.3% relative to the uncompressed setting, improves issue resolution rates by 5.0%-9.2%, and delivers the best overall balance among effectiveness, compression ratio, and latency compared with state-of-the-art context compression baselines.

Related papers

• On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation [22.803236151303846]
  Repository-level code intelligence tasks require large language models to process long, multi-file contexts.<n> Context compression mitigates these risks by condensing inputs.<n>We present the first systematic empirical study of context compression for repository-level code intelligence.
  arXiv  Detail & Related papers  (2026-04-15T11:00:17Z)
• CodeComp: Structural KV Cache Compression for Agentic Coding [31.344543370007568]
  Existing compression methods rely on attention signals to estimate token importance.<n>We present CodeComp, a training-free KV cache compression framework that incorporates static program analysis into LLM inference.<n>CodeComp consistently outperforms attention-only compression baselines under equal memory budgets.
  arXiv  Detail & Related papers  (2026-04-11T14:38:11Z)
• Towards Practical Lossless Neural Compression for LiDAR Point Clouds [84.36825469211375]
  extreme sparsity of high-precision geometric details hinders efficient context modeling.<n>Our framework comprises two lightweight modules.<n>Experiments demonstrate competitive compression performance at real-time speed.
  arXiv  Detail & Related papers  (2026-03-26T10:02:07Z)
• Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression [55.63153956934198]
  Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs)<n>Existing CoT compression methods often suffer from a critical loss of logical fidelity at high compression ratios.<n>We propose a novel EXTreme-RAtio Chain-of-Thought Compression framework, termed Extra-CoT, which aggressively reduces the token budget while preserving answer accuracy.
  arXiv  Detail & Related papers  (2026-02-09T06:57:15Z)
• AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation [27.480791258325066]
  We introduce AttnComp, an adaptive, efficient and context-aware compression framework.<n>AttnComp employs a Top-P compression algorithm to retain the minimal set of documents.<n>In addition to compression, AttnComp estimates response confidence by assessing the overall relevance of the retrieved content.
  arXiv  Detail & Related papers  (2025-09-22T08:18:50Z)
• CORE-RAG: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning [22.93037884068796]
  Retrieval-Augmented Generation (RAG) has emerged as a promising approach to enhance the timeliness of knowledge updates and the factual accuracy of responses in large language models.<n>Existing approaches to document compression tailored for RAG often degrade task performance.<n>We propose CORE, a novel method for lossless context compression in RAG.
  arXiv  Detail & Related papers  (2025-08-24T12:21:50Z)
• Enhancing RAG Efficiency with Adaptive Context Compression [24.94881830262324]
  Retrieval-augmented generation incurs significant inference costs due to lengthy retrieved contexts.<n>Existing methods apply fixed compression rates, over-compressing simple queries or under-compressing complex ones.<n>We propose Adaptive Context Compression for RAG (ACC-RAG), a framework that dynamically adjusts compression rates based on input complexity.
  arXiv  Detail & Related papers  (2025-07-24T13:46:51Z)
• EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation [84.70637613266835]
  EoRA is a fine-tuning-free method that augments compressed Large Language Models with low-rank matrices.<n>EoRA consistently outperforms prior training-free low rank methods in recovering the accuracy of compressed LLMs.
  arXiv  Detail & Related papers  (2024-10-28T17:59:03Z)
• UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective [85.08718140718707]
  UNComp is an uncertainty-aware framework that uncovers sparsity patterns that can be used for adaptive compression.<n>By focusing on uncertainty to analyze the sparsity pattern in detail, UNComp reduces the KV cache size to 4.74% of the original, achieves a 6% prefill speedup, and improves throughput by 6.4x.
  arXiv  Detail & Related papers  (2024-10-04T02:32:36Z)
• Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference [16.830389144259584]
  We propose context-aware prompt compression (CPC), a sentence-level prompt compression technique.<n>Key innovation is a novel context-aware sentence encoder that provides a relevance score for each sentence for a given question.<n>Our method considerably outperforms prior works on prompt compression on benchmark datasets.
  arXiv  Detail & Related papers  (2024-09-02T13:02:51Z)
• Differential error feedback for communication-efficient decentralized learning [48.924131251745266]
  We propose a new decentralized communication-efficient learning approach that blends differential quantization with error feedback. We show that the resulting communication-efficient strategy is stable both in terms of mean-square error and average bit rate. The results establish that, in the small step-size regime and with a finite number of bits, it is possible to attain the performance achievable in the absence of compression.
  arXiv  Detail & Related papers  (2024-06-26T15:11:26Z)
• In-Context Former: Lightning-fast Compressing Context for Large Language Model [48.831304302467004]
  In this paper, we propose a new approach to compress the long input contexts of Transformer-based large language models (LLMs) We use the cross-attention mechanism and a small number of learnable digest tokens to condense information from the contextual word embeddings. Experimental results indicate that our method requires only 1/32 of the floating-point operations of the baseline during compression and improves processing speed by 68 to 112 times.
  arXiv  Detail & Related papers  (2024-06-19T15:14:55Z)

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.