# AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse

arXiv: https://arxiv.org/abs/2605.03644 · HTML: https://mlsanity.com/paper/2605.03644/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 5 May 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [In-Context Learning with Long-Context Models: An In-Depth Exploration](https://mlsanity.com/paper/2405.00200/) (2024)
- [The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning](https://mlsanity.com/paper/2305.14045/) (2023)
- [Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition](https://mlsanity.com/paper/2505.22375/) (2025)
- [ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2502.00299/) (2025)
- [In-Context Learning with Many Demonstration Examples](https://mlsanity.com/paper/2302.04931/) (2023)
- [Star Attention: Efficient LLM Inference over Long Sequences](https://mlsanity.com/paper/2411.17116/) (2024)
- [Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning](https://mlsanity.com/paper/2410.04691/) (2024)
- [From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation](https://mlsanity.com/paper/2502.00330/) (2025)
- [Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain](https://mlsanity.com/paper/2602.09794/) (2026)
- [When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training](https://mlsanity.com/paper/2411.13476/) (2024)
- [MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning](https://mlsanity.com/paper/2505.16225/) (2025)
- [Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention](https://mlsanity.com/paper/2503.08640/) (2025)
- [On Many-Shot In-Context Learning for Long-Context Evaluation](https://mlsanity.com/paper/2411.07130/) (2024)
- [Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models](https://mlsanity.com/paper/2603.13394/) (2026)
- [Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations](https://mlsanity.com/paper/2503.03062/) (2025)
- [Many-Shot In-Context Learning for Molecular Inverse Design](https://mlsanity.com/paper/2407.19089/) (2024)
- [Towards Compute-Optimal Many-Shot In-Context Learning](https://mlsanity.com/paper/2507.16217/) (2025)

## Built on by (most cited first, 1 of 1)

- [MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression](https://mlsanity.com/paper/2609.29913/) (2026)

## Abstract (arXiv)

Many-Shot In-Context Learning (ICL) has emerged as a promising paradigm, leveraging extensive examples to unlock the reasoning potential of Large Language Models (LLMs). However, existing methods typically rely on a predetermined, fixed number of shots. This static approach often fails to adapt to the varying difficulty of different queries, leading to either insufficient context or interference from noise. Furthermore, the prohibitive computational and memory costs of long contexts severely limit Many-Shot's feasibility. To address the above limitations, we propose AdapShot, which dynamically optimizes shot counts and leverages KV cache reuse for efficient inference. Specifically, we design a probe-based evaluation mechanism that utilizes output entropy to determine the optimal number of shots. To bypass the redundant prefilling computation during both the probing and inference phases, we incorporate a semantics-aware KV cache reuse strategy. Within this reuse strategy, to address positional encoding incompatibilities, we introduce a decoupling and re-encoding method that enables the flexible reordering of cached key-value pairs. Extensive experiments demonstrate that AdapShot achieves an average performance gain of around 10% and a 4.64x speedup compared to state-of-the-art DBSA.