Atropos uses GCN on inference graphs for early failure prediction and hotswaps to larger LLMs, achieving 74% of large-model performance at 24% cost.
A preliminary evaluation of llm-based fault localization
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.SE 4verdicts
UNVERDICTED 4representative citing papers
Healer uses LLMs to dynamically generate and execute runtime error-handling code, with GPT-4 recovering from 72.8% of errors across four datasets.
TransAgent improves LLM code translation by up to 33.3% via multi-agent fine-grained execution alignment on a new benchmark of recent tasks.
Locally deployed LLMs achieve 43-45% accuracy on Python bug detection but frequently produce only partial identifications of problematic code regions.
citing papers explorer
-
Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap
Atropos uses GCN on inference graphs for early failure prediction and hotswaps to larger LLMs, achieving 74% of large-model performance at 24% cost.
-
Towards Agentic Runtime Healing
Healer uses LLMs to dynamically generate and execute runtime error-handling code, with GPT-4 recovering from 72.8% of errors across four datasets.
-
TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment
TransAgent improves LLM code translation by up to 33.3% via multi-agent fine-grained execution alignment on a new benchmark of recent tasks.
-
An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code
Locally deployed LLMs achieve 43-45% accuracy on Python bug detection but frequently produce only partial identifications of problematic code regions.