RULER shows most long-context LMs drop sharply in performance on complex tasks as length and difficulty increase, with only half maintaining results at 32K tokens.
hub Canonical reference
Longllmlingua: Accelerating and enhancing llms in long context scenarios via prompt compression
Canonical reference. 75% of citing Pith papers cite this work as background.
16
Pith papers citing it
Background
75% of classified citations
hub tools
citation-role summary
background 7
baseline 1
citation-polarity summary
representative citing papers
TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.
Continuous latent-vector compression improves BLEU scores on repository-level code tasks by up to 28.3% at 4x compression while cutting inference latency.
A unified compressed-sensing framework enables dynamic, task- and token-adaptive structured reduction of LLMs with formal sample-complexity bounds.
R1-Searcher uses two-stage outcome-based RL to train LLMs to invoke external search systems for better reasoning without process rewards or distillation.
LIFT fine-tunes short-context LLMs on long inputs with synthetic tasks to absorb information into parameters, enabling answers without the input present at inference.
CodePromptZip builds a code compressor via type-aware ablation-ranked training samples and a copy-augmented small LM, reporting 23.4-28.7% gains over baselines on three RAG coding tasks.
Search-o1 integrates agentic retrieval-augmented generation and a Reason-in-Documents module into large reasoning models to dynamically supply missing knowledge and improve performance on complex science, math, coding, and QA tasks.
LLM-based autonomous semantic compression in four 2D UAV swarm simulations shows potential for efficient collaborative communication under bandwidth constraints.
E2LLM uses encoder-based soft prompt compression for long contexts to improve LLM reasoning on tasks like summarization and QA while maintaining efficiency.
AdaComp trains a compression-rate predictor on annotated minimum top-k data to adaptively retain only the documents needed for each RAG query.
Byte-exact deduplication reduces RAG context size by 0.16% to 80.34% across three regimes with zero measurable quality regression per multi-vendor LLM evaluation.
SGT trains a lightweight model to generate task-specific supplemental text that improves performance of a larger frozen LLM on agentic tasks without modifying the large model.
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
citing papers explorer
-
RULER: What's the Real Context Size of Your Long-Context Language Models?
RULER shows most long-context LMs drop sharply in performance on complex tasks as length and difficulty increase, with only half maintaining results at 32K tokens.
-
TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments
TSCG compiles JSON tool schemas into token-efficient structured text, raising tool-use accuracy for small LLMs from 0% to 84.4% on benchmarks while cutting tokens by 52-57%.
-
On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation
Continuous latent-vector compression improves BLEU scores on repository-level code tasks by up to 28.3% at 4x compression while cutting inference latency.
-
Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models
A unified compressed-sensing framework enables dynamic, task- and token-adaptive structured reduction of LLMs with formal sample-complexity bounds.
-
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
R1-Searcher uses two-stage outcome-based RL to train LLMs to invoke external search systems for better reasoning without process rewards or distillation.
-
LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning
LIFT fine-tunes short-context LLMs on long inputs with synthetic tasks to absorb information into parameters, enabling answers without the input present at inference.
-
CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs
CodePromptZip builds a code compressor via type-aware ablation-ranked training samples and a copy-augmented small LM, reporting 23.4-28.7% gains over baselines on three RAG coding tasks.
-
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Search-o1 integrates agentic retrieval-augmented generation and a Reason-in-Documents module into large reasoning models to dynamically supply missing knowledge and improve performance on complex science, math, coding, and QA tasks.
-
Talk Less, Fly Lighter: Autonomous Semantic Compression for UAV Swarm Communication via LLMs
LLM-based autonomous semantic compression in four 2D UAV swarm simulations shows potential for efficient collaborative communication under bandwidth constraints.
-
E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning
E2LLM uses encoder-based soft prompt compression for long contexts to improve LLM reasoning on tasks like summarization and QA while maintaining efficiency.
-
AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models
AdaComp trains a compression-rate predictor on annotated minimum top-k data to adaptively retain only the documents needed for each RAG query.
-
Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks
Byte-exact deduplication reduces RAG context size by 0.16% to 80.34% across three regimes with zero measurable quality regression per multi-vendor LLM evaluation.
-
Supplement Generation Training for Enhancing Agentic Task Performance
SGT trains a lightweight model to generate task-specific supplemental text that improves performance of a larger frozen LLM on agentic tasks without modifying the large model.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
-
Retrieval-Augmented Generation for Large Language Models: A Survey
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
- Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations