SGKR uses function-call dependency graphs to retrieve structured code knowledge, improving LLM correctness on multi-step data reasoning benchmarks over similarity baselines.
Llm/agent-as-data-analyst: A survey
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
EvoDS adds autonomous skill acquisition via synthesis-validation-reuse and adaptive context compression via learned control within a two-stage multi-agent RL scheme, claiming 28.9% average gains over prior agents on four benchmarks plus elimination of out-of-token failures.
K-Token Merging compresses LLM inputs by merging blocks of K token embeddings in latent space, achieving up to 75% length reduction with minimal performance drop on reasoning, classification, and code tasks.
A literature survey that taxonomizes methods, datasets, and evaluation practices for natural language interfaces to geospatial and temporal databases while identifying recurring trends and future directions.
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
citing papers explorer
-
Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions
A literature survey that taxonomizes methods, datasets, and evaluation practices for natural language interfaces to geospatial and temporal databases while identifying recurring trends and future directions.