Position: Agentic Evolution is the Path to Evolving LLMs

• URL: http://arxiv.org/abs/2602.00359v1
• Date: Fri, 30 Jan 2026 22:15:58 GMT
• Title: Position: Agentic Evolution is the Path to Evolving LLMs
• Authors: Minhua Lin, Hanqing Lu, Zhan Shi, Bing He, Rui Mao, Zhiwei Zhang, Zongyu Wu, Xianfeng Tang, Hui Liu, Zhenwei Dai, Xiang Zhang, Suhang Wang, Benoit Dumoulin, Jian Pei,
• Abstract summary: We argue that addressing this limitation requires a new scaling axis-evolution.<n>Existing deployment-time adaptation methods lack the strategic agency needed to diagnose failures and produce durable improvements.
• Score: 56.733933092220845
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time and inference-time compute improves static capability but does not close this train-deploy gap. We argue that addressing this limitation requires a new scaling axis-evolution. Existing deployment-time adaptation methods, whether parametric fine-tuning or heuristic memory accumulation, lack the strategic agency needed to diagnose failures and produce durable improvements. Our position is that agentic evolution represents the inevitable future of LLM adaptation, elevating evolution itself from a fixed pipeline to an autonomous evolver agent. We instantiate this vision in a general framework, A-Evolve, which treats deployment-time improvement as a deliberate, goal-directed optimization process over persistent system state. We further propose the evolution-scaling hypothesis: the capacity for adaptation scales with the compute allocated to evolution, positioning agentic evolution as a scalable path toward sustained, open-ended adaptation in the real world.

Related papers

• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization [61.535567824938205]
  We introduce AdaEvolve, a framework that reformulates LLM-driven evolution as a hierarchical adaptive optimization problem.<n>AdaEvolve consistently outperforms the open-ended baselines across 185 different open-ended optimization problems.
  arXiv  Detail & Related papers  (2026-02-23T18:45:31Z)
• AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection [14.17960333915609]
  Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability.<n>We introduce AdaptEvolve: Adaptive Selection for Multi-LLM Evolutionary Refinement.
  arXiv  Detail & Related papers  (2026-02-12T13:26:56Z)
• Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks [10.622439192272527]
  Conventional agent systems struggle in open-ended environments where task distributions continuously drift and external supervision is scarce.<n>We propose the In-Situ Self-Evolving paradigm, which treats sequential task interactions as a continuous stream of experience.<n>Within this framework, we develop Yunjue Agent, a system that iteratively synthesizes, optimize, and reuses tools to navigate emerging challenges.
  arXiv  Detail & Related papers  (2026-01-26T07:27:47Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning [79.59753528758361]
  We present TrajBooster, a cross-embodiment framework that leverages abundant wheeled-humanoid data to boost bipedal VLA.<n>Our key idea is to use end-effector trajectories as a morphology-agnostic interface.<n>Results show that TrajBooster allows existing wheeled-humanoid data to efficiently strengthen bipedal humanoid VLA performance.
  arXiv  Detail & Related papers  (2025-09-15T12:25:39Z)
• A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence [87.08051686357206]
  Large Language Models (LLMs) have demonstrated strong capabilities but remain fundamentally static.<n>As LLMs are increasingly deployed in open-ended, interactive environments, this static nature has become a critical bottleneck.<n>This survey provides the first systematic and comprehensive review of self-evolving agents.
  arXiv  Detail & Related papers  (2025-07-28T17:59:05Z)
• Predictability Shapes Adaptation: An Evolutionary Perspective on Modes of Learning in Transformers [51.992454203752686]
  Transformer models learn in two distinct modes: in-weights learning (IWL) and in-context learning (ICL)<n>We draw inspiration from evolutionary biology's analogous adaptive strategies: genetic encoding and phenotypic plasticity.<n>We experimentally operationalize these dimensions of predictability and investigate their influence on the ICL/IWL balance in Transformers.
  arXiv  Detail & Related papers  (2025-05-14T23:31:17Z)
• Agent Alignment in Evolving Social Norms [65.45423591744434]
  We propose an evolutionary framework for agent evolution and alignment, named EvolutionaryAgent. In an environment where social norms continuously evolve, agents better adapted to the current social norms will have a higher probability of survival and proliferation. We show that EvolutionaryAgent can align progressively better with the evolving social norms while maintaining its proficiency in general tasks.
  arXiv  Detail & Related papers  (2024-01-09T15:44:44Z)
• From Self-Adaptation to Self-Evolution Leveraging the Operational Design Domain [15.705888799637506]
  Self-adaptation has shown to be a viable approach to dealing with changing conditions. The capabilities of a self-adaptive system are constrained by its operational design domain (ODD) We provide a definition for ODD and apply it to a self-adaptive system.
  arXiv  Detail & Related papers  (2023-03-27T14:49:07Z)

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.