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%.
Title resolution pending
9 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
9
Pith papers citing it
3
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Reasoning language models extract answers from sparse, order-shuffled chain-of-thought traces with little accuracy loss.
MemAgent trains an LLM with reinforcement learning to maintain a fixed-size token memory while reading a long document in chunks, and reports near-lossless QA accuracy extrapolating from 32K training context to 3.5M test tokens.
LLMs implicitly identify informative context in early layers, enabling a linear prober to drop noisy chunks and improve both performance and efficiency across tasks and models.
InfoKV is an entropy-aware KV cache compression framework that integrates token-level predictive uncertainty and layer-wise representation evolution with attention scores to improve performance on long-context reasoning benchmarks.
SSAS improves LLM sentiment prediction consistency and data quality by up to 30% on three review datasets via syntactic and semantic context assessment summarization.
AdaComp trains a compression-rate predictor on annotated minimum top-k data to adaptively retain only the documents needed for each RAG query.
wSSAS is a two-phase deterministic framework that uses hierarchical text organization and SNR-based feature prioritization to improve clustering integrity, categorization accuracy, and reproducibility when applying LLMs to large review datasets.
Entropy Gate applies entropy quenching with adaptive temperature schedules and multi-factor token energies to achieve 40-60% compression in LLM prompts while keeping semantic similarity above 0.80.
citing papers explorer
-
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%.
-
Rethinking Dense Sequential Chains: Reasoning Language Models Can Extract Answers from Sparse, Order-Shuffling Chain-of-Thoughts
Reasoning language models extract answers from sparse, order-shuffled chain-of-thought traces with little accuracy loss.
-
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
MemAgent trains an LLM with reinforcement learning to maintain a fixed-size token memory while reading a long document in chunks, and reports near-lossless QA accuracy extrapolating from 32K training context to 3.5M test tokens.
-
END: Early Noise Dropping for Efficient and Effective Context Denoising
LLMs implicitly identify informative context in early layers, enabling a linear prober to drop noisy chunks and improve both performance and efficiency across tasks and models.
-
Information-Aware KV Cache Compression for Long Reasoning
InfoKV is an entropy-aware KV cache compression framework that integrates token-level predictive uncertainty and layer-wise representation evolution with attention scores to improve performance on long-context reasoning benchmarks.
-
Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)
SSAS improves LLM sentiment prediction consistency and data quality by up to 30% on three review datasets via syntactic and semantic context assessment summarization.
-
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.
-
Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs
wSSAS is a two-phase deterministic framework that uses hierarchical text organization and SNR-based feature prioritization to improve clustering integrity, categorization accuracy, and reproducibility when applying LLMs to large review datasets.
-
Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines
Entropy Gate applies entropy quenching with adaptive temperature schedules and multi-factor token energies to achieve 40-60% compression in LLM prompts while keeping semantic similarity above 0.80.