CGFuse enables deep token-level fusion of graph-derived structural features into language models, yielding 10-16% BLEU and 6-11% CodeBLEU gains on code generation tasks.
https://arxiv
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
DiagramBank is a large-scale curated dataset of 89,422 schematic diagrams from scientific papers with rich metadata to support multimodal retrieval and exemplar-driven figure generation.
A structured survey organizing graph-LLM integration methods by purpose, modality, and strategy across application domains.
Graphectory turns stochastic agent trajectories into analyzable graphs, showing that stronger models and successful fixes follow coherent localization-validation steps while failures are chaotic, and online detection plus rollback improves resolution rates by 6.9-23.5%.
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
SWE-AGILE introduces a Dynamic Reasoning Context with sliding windows of detailed steps and compressed Reasoning Digests to enable efficient long-horizon reasoning in software engineering agents, claiming new benchmark results on SWE-Bench-Verified for 7B-8B models.
Graphs can help LLMs reduce hallucinations, boost reasoning via prompting techniques, and better process structured data.
citing papers explorer
-
Deep Graph-Language Fusion for Structure-Aware Code Generation
CGFuse enables deep token-level fusion of graph-derived structural features into language models, yielding 10-16% BLEU and 6-11% CodeBLEU gains on code generation tasks.
-
DiagramBank: A Large-scale Dataset of Diagram Design Exemplars with Paper Metadata for Retrieval-Augmented Generation
DiagramBank is a large-scale curated dataset of 89,422 schematic diagrams from scientific papers with rich metadata to support multimodal retrieval and exemplar-driven figure generation.
-
Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval
A structured survey organizing graph-LLM integration methods by purpose, modality, and strategy across application domains.
-
Process-Centric Analysis of Agentic Software Systems
Graphectory turns stochastic agent trajectories into analyzable graphs, showing that stronger models and successful fixes follow coherent localization-validation steps while failures are chaotic, and online detection plus rollback improves resolution rates by 6.9-23.5%.
-
Code as Agent Harness
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
-
SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
SWE-AGILE introduces a Dynamic Reasoning Context with sliding windows of detailed steps and compressed Reasoning Digests to enable efficient long-horizon reasoning in software engineering agents, claiming new benchmark results on SWE-Bench-Verified for 7B-8B models.
-
Position: How can Graphs Help Large Language Models?
Graphs can help LLMs reduce hallucinations, boost reasoning via prompting techniques, and better process structured data.