Layer-wise Token Compression applies adaptive token pooling at middle transformer layers for cross-encoder rerankers, preserving MS MARCO ranking quality while raising QPS up to 25% on passages and 116% on documents, with added gains on listwise LLM rerankers and a regularizer effect for long inputs
Prompt compression for large language models: A survey
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Leveraging large language models (LLMs) for complex natural language tasks typically requires long-form prompts to convey detailed requirements and information, which results in increased memory usage and inference costs. To mitigate these challenges, multiple efficient methods have been proposed, with prompt compression gaining significant research interest. This survey provides an overview of prompt compression techniques, categorized into hard prompt methods and soft prompt methods. First, the technical approaches of these methods are compared, followed by an exploration of various ways to understand their mechanisms, including the perspectives of attention optimization, Parameter-Efficient Fine-Tuning (PEFT), modality integration, and new synthetic language. We also examine the downstream adaptations of various prompt compression techniques. Finally, the limitations of current prompt compression methods are analyzed, and several future directions are outlined, such as optimizing the compression encoder, combining hard and soft prompts methods, and leveraging insights from multimodality.
years
2026 5representative citing papers
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
ECHO stores each agent turn as a source-indexed memory, reconstructs bounded contexts by selecting useful records, and routes RL credit through the same selection trace — reaching 43.4% on BrowseComp-Plus vs 28.9% (GRPO) and 36.1% (SUPO).
Mem-π is a framework using a dedicated model and decision-content decoupled RL to generate context-specific guidance on demand for LLM agents, outperforming retrieval baselines by over 30% on web navigation.
CORE is a lightweight two-stage prompt compression method for edge-device RAG QA that builds answer and clue sets via NER and semantic matching then refines them to deliver higher accuracy and lower resource costs than baselines.
citing papers explorer
-
Layer-wise Token Compression for Efficient Document Reranking
Layer-wise Token Compression applies adaptive token pooling at middle transformer layers for cross-encoder rerankers, preserving MS MARCO ranking quality while raising QPS up to 25% on passages and 116% on documents, with added gains on listwise LLM rerankers and a regularizer effect for long inputs
-
What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
-
ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL
ECHO stores each agent turn as a source-indexed memory, reconstructs bounded contexts by selecting useful records, and routes RL credit through the same selection trace — reaching 43.4% on BrowseComp-Plus vs 28.9% (GRPO) and 36.1% (SUPO).
-
Mem-$\pi$: Adaptive Memory through Learning When and What to Generate
Mem-π is a framework using a dedicated model and decision-content decoupled RL to generate context-specific guidance on demand for LLM agents, outperforming retrieval baselines by over 30% on web navigation.
-
Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices
CORE is a lightweight two-stage prompt compression method for edge-device RAG QA that builds answer and clue sets via NER and semantic matching then refines them to deliver higher accuracy and lower resource costs than baselines.