AEL: Evolving Agent Harness in Open-Ended Environments

arXiv:2604.21725 · cs.CL, cs.AI, cs.CE · Submitted 2026-04-23 · Read on arXiv

cs.CL, cs.AI, cs.CE

Submitted: 2026-04-23

Updated: 2026-08-25

Comments: EMNLP 2026 Findings

Code: https://github.com/WujiangXu/AEL

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Credit assignment — 22× in this paper · explained in 3 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Ablation — 16× in this paper · explained in 1 episode
• Adaptation — 7× in this paper · explained in 1 episode
• Accuracy — 4× in this paper · explained in 1 episode
• Agent Evolving Learning — 4× in this paper
• Distillation — 4× in this paper · explained in 2 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Robustness — 3× in this paper · explained in 5 episodes
• alpha — 3× in this paper
• Action Space — 2× in this paper · explained in 1 episode
• Adaptive Mechanism — 2× in this paper · explained in 1 episode
• Admissibility — 2× in this paper · explained in 2 episodes
• Allocator — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 3 episodes
• Adaptive Strategy — 1× in this paper · explained in 1 episode
• Agent Harness — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Contextual Bandits — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Metacognition — 1× in this paper · explained in 5 episodes
• Modular Components — 1× in this paper · explained in 2 episodes
• Modularity — 1× in this paper · explained in 9 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Shapley values — 1× in this paper · explained in 2 episodes
• Systematic Bias — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Understanding the planning of LLM agents: A survey
• MemGPT: Towards LLMs as Operating Systems
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents
• FactorMiner: A Self-Evolving Agent with Skills and Experience Memory for Financial Alpha Discovery
• Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent
• Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent
• A-MEM: Agentic Memory for LLM Agents
• EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering