Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization

• URL: http://arxiv.org/abs/2604.23472v1
• Date: Sat, 25 Apr 2026 23:46:08 GMT
• Title: Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization
• Abstract summary: Escher-Loop is a framework that operationalizes the evolution of two distinct populations: Task Agents that solve problems, and Agents that refine both the task agents and themselves.<n>We show that Escher-Loop effectively pushes past the performance ceilings of static baselines, achieving the highest absolute peak performance.<n>Remarkably, we observe that agents dynamically adapt their strategies to match the shifting demands of high-performing task agents, which explains the system's continuous improvement and superior late-stage performance.
• Score: 7.89766538351877
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While recent autonomous agents demonstrate impressive capabilities, they predominantly rely on manually scripted workflows and handcrafted heuristics, inherently limiting their potential for open-ended improvement. To address this, we propose Escher-Loop, a fully closed-loop framework that operationalizes the mutual evolution of two distinct populations: Task Agents that solve concrete problems, and Optimizer Agents that recursively refine both the task agents and themselves. To sustain this self-referential evolution, we propose a dynamic benchmarking mechanism that seamlessly reuses the empirical scores of newly generated task agents as relative win-loss signals to update optimizers' scores. This mechanism leverages the evolution of task agents as an inherent signal to drive the evaluation and refinement of optimizers without additional overhead. Empirical evaluations on mathematical optimization problems demonstrate that Escher-Loop effectively pushes past the performance ceilings of static baselines, achieving the highest absolute peak performance across all evaluated tasks under matched compute. Remarkably, we observe that the optimizer agents dynamically adapt their strategies to match the shifting demands of high-performing task agents, which explains the system's continuous improvement and superior late-stage performance.

Related papers

• Self-evolving LLM agents with in-distribution Optimization [60.05867547965365]
  Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments.<n>We propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning.<n>We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance.
  arXiv  Detail & Related papers  (2026-06-05T15:09:52Z)
• Evolutionary Ensemble of Agents [7.465452178698495]
  We introduce EvE, a decentralized framework that organizes coding agents into a live, co-evolving system for algorithmic discovery.<n>By maintaining two co-evolving populations, EvE evaluates agents through a synchronous race, updating their empirical Elo ratings.<n>Compared to variants driven by a fixed initial agent or even a frozen "best-evolved" agent, EvE uniquely avoids phase mismatch.
  arXiv  Detail & Related papers  (2026-05-09T15:56:10Z)
• VeRO: An Evaluation Harness for Agents to Optimize Agents [5.227525836910522]
  We introduce VERO (Versioning, Rewards, and Observations), which provides a reproducible evaluation harness with versioned agent snapshots, budget-controlled evaluation, and structured execution traces.<n>We conduct an empirical study comparing target agents and analyzing which modifications reliably improve target agent performance.
  arXiv  Detail & Related papers  (2026-02-25T23:40:22Z)
• TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents [43.376952807616256]
  Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment.<n>We propose Test-time Improvement Diagnostic Evaluation (TIDE), an agent-agnostic and environment-agnostic framework that decomposes TTI into three comprehensive and interconnected dimensions.
  arXiv  Detail & Related papers  (2026-02-02T15:00:47Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Agentic Predictor: Performance Prediction for Agentic Workflows via Multi-View Encoding [56.565200973244146]
  Agentic Predictor is a lightweight predictor for efficient agentic workflow evaluation.<n>By learning to approximate task success rates, Agentic Predictor enables fast and accurate selection of optimal agentic workflow configurations.
  arXiv  Detail & Related papers  (2025-05-26T09:46:50Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [112.04307762405669]
  G"odel Agent is a self-evolving framework inspired by the G"odel machine.<n>G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-10-06T10:49:40Z)
• Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement [50.481380478458945]
  Iterative step-level Process Refinement (IPR) framework provides detailed step-by-step guidance to enhance agent training. Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines.
  arXiv  Detail & Related papers  (2024-06-17T03:29:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.