LLM-as-Code: Agentic Programming for Agent Harness
cs.AI, cs.SE
Submitted: 2026-06-14
Updated: 2026-11-09
Comments: Accepted at the KDD 2026 Workshop on Agentic Software Engineering (AgenticSE)
Code: https://github.com/langchain-ai/langgraph
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories
- Scaling Agents for Computer Use
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
- Can LLMs Follow Simple Rules?
- Large Language Models Can Be Easily Distracted by Irrelevant Context
- Executable Code Actions Elicit Better LLM Agents
- OpenHands: An Open Platform for AI Software Developers as Generalist Agents
- The Rise and Potential of Large Language Model Based Agents: A Survey
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents