Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor

• URL: http://arxiv.org/abs/2605.28713v1
• Date: Wed, 27 May 2026 16:36:01 GMT
• Title: Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor
• Abstract summary: This work reveals that a thinking model itself can naturally compress long contexts by organizing task-relevant information.<n>We thus derive Thinking as Compression (TaC), a new compression paradigm that treats thinking itself as compressed context.
• Score: 18.235525350999335
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Context compression aims to shorten long context inputs with minimal information loss for LLM inference acceleration. While existing methods have shown promise, they typically rely on complex compression modules or compression-specific training, leaving the intrinsic capabilities of LLMs underexplored. In contrast, this work reveals that a thinking model itself can naturally compress long contexts by organizing task-relevant information. We thus derive Thinking as Compression (TaC), a new compression paradigm that treats thinking itself as compressed context. Without relying on specific dedicated compressor, TaC directly prompts the thinking model to generate thinking traces as the shortened context, already outperforming most representative compression methods. Further, given that raw thinking output may struggle with budget control and shortcut behaviors, we introduce Thinking as Compression Constrained (TaC-C), leveraging a simple reward-driven optimization framework to elicit intrinsic thinking as compact and controllable compressed context. Experiments across four long-context QA benchmarks demonstrate that TaC-C consistently outperforms existing baselines. At 4x and 8x compression ratios, it surpasses the strongest competitor by 17.4% and 23.4% in average F1, and by 15.7% and 21.7% in average Exact Match Score (EM), respectively.

Related papers

• End-to-End Context Compression at Scale [81.70601323130997]
  Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.<n>Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.<n>Existing approaches are not competitive with KV cache compression on the accuracy-efficiency frontier.
  arXiv  Detail & Related papers  (2026-06-08T15:43:16Z)
• Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio [19.375601589555327]
  We introduce Semi-Dynamic Context Compression framework.<n>Our approach features a Discrete Ratio Selector, which predicts a compression target based on intrinsic information density.<n>Our framework consistently outperforms static baselines.
  arXiv  Detail & Related papers  (2026-03-26T21:36:55Z)
• PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction [40.705016911274]
  We introduce a paradigm shift to Performance-oriented Context Compression (PoC)<n>PoC employs a lightweight performance predictor to automatically find the most aggressive compression ratio.<n>Our work paves the way for a more reliable, efficient, and performance-aware deployment of context compression for Large Language Models.
  arXiv  Detail & Related papers  (2026-03-20T08:18:46Z)
• Arbitrary Ratio Feature Compression via Next Token Prediction [52.10426317889982]
  Arbitrary Ratio Feature Compression (ARFC) framework supports any compression ratio with a single model.<n>ARC is an auto-regressive model that performs compression via next-gressive prediction.<n>MoS module refines the compressed tokens by utilizing multiple compression results.<n>ERGC is integrated into the training process to preserve semantic and structural relationships during compression.
  arXiv  Detail & Related papers  (2026-02-12T02:38:57Z)
• 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)
• Simple Context Compression: Mean-Pooling and Multi-Ratio Training [12.049015994907629]
  We develop a lightweight and simple mean-pooling approach that consistently outperforms the widely used compression-tokens architecture.<n>We conduct extensive experiments across in-domain and out-of-domain QA datasets, as well as across model families, scales, and compression ratios.<n>Overall, our simple mean-pooling approach achieves the strongest performance, with a relatively small drop when training for multiple compression ratios.
  arXiv  Detail & Related papers  (2025-10-23T17:57:23Z)
• Compressing Many-Shots in In-Context Learning [61.231471139896506]
  We study an approach to improve the memory and computational efficiency of ICL inference by compressing the many-shot prompts.<n>We first show that existing prompt compression methods are ineffective for many-shot compression.<n>We propose MemCom, a layer-wise compression method.
  arXiv  Detail & Related papers  (2025-10-17T16:57:42Z)
• Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors [43.02557489472655]
  Current context compression methods rely on autoencoding tasks to train context-agnostic compression tokens to compress contextual semantics.<n>We propose Semantic-Anchor Compression (SAC), a novel method that shifts from autoencoding task based compression to an architecture that is equipped with this compression capability.<n>SAC consistently outperforms existing context compression methods across various compression ratios.
  arXiv  Detail & Related papers  (2025-10-10T01:42:14Z)
• CompLLM: Compression for Long Context Q&A [47.90063873976842]
  We introduce CompLLM, a soft compression technique designed for practical deployment.<n>Instead of processing the context holistically, CompLLM divides it into segments and compresses each one independently.<n>Our experiments show that with a 2x compression rate, at high context lengths CompLLM speeds up Time To First Token (TTFT) by up to 4x and reduces the KV cache size by 50%.
  arXiv  Detail & Related papers  (2025-09-23T16:49:43Z)
• 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.