Chat2Workflow benchmark shows that state-of-the-art LLMs often grasp high-level intent for visual workflow generation but fail to produce correct, stable, executable outputs, with an agentic framework delivering only modest 5.34% gains.
WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Lan- guage Models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
LEMON trains an LLM orchestrator with counterfactual-augmented GRPO to produce deployable multi-agent specifications that reach state-of-the-art results on six reasoning and coding benchmarks.
Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.
A systems-level data model for preserving typed, addressable, versioned, and dependency-aware intermediate artifacts in agentic AI systems to improve long-term inspectability and maintainability.
Execution lineage models AI-native work as a DAG of computations with explicit dependencies, achieving perfect state preservation in controlled update tasks where loop-based agents introduce churn and contamination.
Compiled AI generates deterministic code artifacts from LLMs in a one-time compilation step, enabling reliable workflow execution with zero runtime tokens after break-even.
citing papers explorer
-
Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language
Chat2Workflow benchmark shows that state-of-the-art LLMs often grasp high-level intent for visual workflow generation but fail to produce correct, stable, executable outputs, with an agentic framework delivering only modest 5.34% gains.
-
LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning
LEMON trains an LLM orchestrator with counterfactual-augmented GRPO to produce deployable multi-agent specifications that reach state-of-the-art results on six reasoning and coding benchmarks.
-
Why Does Agentic Safety Fail to Generalize Across Tasks?
Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.
-
Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems
A systems-level data model for preserving typed, addressable, versioned, and dependency-aware intermediate artifacts in agentic AI systems to improve long-term inspectability and maintainability.
-
From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work
Execution lineage models AI-native work as a DAG of computations with explicit dependencies, achieving perfect state preservation in controlled update tasks where loop-based agents introduce churn and contamination.
-
Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation
Compiled AI generates deterministic code artifacts from LLMs in a one-time compilation step, enabling reliable workflow execution with zero runtime tokens after break-even.