Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks
cs.AI, cs.CL, cs.MA
Submitted: 2026-11-01
Updated: 2026-11-01
Comments: Accepted as a Spotlight at the NeurIPS 2026 Workshop on Interpreting Agent Behavior (IAB), GLEE Competition Track; 1st place in the GLEE competition. 21 pages
Code: https://github.com/fzkuji-neo/OpenProgram
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Agents of Change: Self-Evolving LLM Agents for Strategic Planning
- SEW: Self-Evolving Agentic Workflows for Automated Code Generation
- LLM-as-Code: Agentic Programming for Agent Harness
- GLEE: A Unified Framework and Benchmark for Language-based Economic Environments
- HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning
- Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents
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