StepFly automates TSG execution via TSG Mentor, LLM-based DAG extraction with QPPs, and a DAG-guided parallel scheduler, reaching 94% success on GPT-4.1 with 32.9-70.4% time savings on parallelizable guides.
Aios compiler: Llm as interpreter for natural language programming and flow programming of ai agents
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
PRIMETIME generator reveals that LLM datetime parsing and arithmetic primitives are individually unreliable but fully learnable via fine-tuning, enabling frontier-level accuracy on event planning with small LoRA models.
The paper defines intent-to-execution integrity as the conjunction of Tool Integrity, Instruction Integrity, Judgment Integrity, and Data Flow Integrity, arguing that existing LLM agent defenses provide only partial coverage of these properties.
Optimizing code for semantic density rather than human readability can improve agentic AI development efficiency, but aggressive compression of logs increased overall costs by shifting burden to reasoning.
citing papers explorer
-
StepFly: Agentic Troubleshooting Guide Automation for Incident Diagnosis
StepFly automates TSG execution via TSG Mentor, LLM-based DAG extraction with QPPs, and a DAG-guided parallel scheduler, reaching 94% success on GPT-4.1 with 32.9-70.4% time savings on parallelizable guides.
-
PRIMETIME : Limits of LLMs in Temporal Primitives
PRIMETIME generator reveals that LLM datetime parsing and arithmetic primitives are individually unreliable but fully learnable via fine-tuning, enabling frontier-level accuracy on event planning with small LoRA models.
-
Securing LLM Agents Need Intent-to-Execution Integrity
The paper defines intent-to-execution integrity as the conjunction of Tool Integrity, Instruction Integrity, Judgment Integrity, and Data Flow Integrity, arguing that existing LLM agent defenses provide only partial coverage of these properties.
-
Beyond Human-Readable: Rethinking Software Engineering Conventions for the Agentic Development Era
Optimizing code for semantic density rather than human readability can improve agentic AI development efficiency, but aggressive compression of logs increased overall costs by shifting burden to reasoning.