Learning Without Losing Identity: Capability Evolution for Embodied Agents

• URL: http://arxiv.org/abs/2604.07799v1
• Date: Thu, 09 Apr 2026 04:51:07 GMT
• Title: Learning Without Losing Identity: Capability Evolution for Embodied Agents
• Abstract summary: We propose a capability-centric evolution paradigm for embodied agents.<n>We argue that a robot should maintain a persistent agent as its cognitive identity.<n>We present a unified framework in which capability evolution is decoupled from agent identity.
• Score: 14.412476605788482
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing approaches to improving agent performance often rely on modifying the agent itself -- through prompt engineering, policy updates, or structural redesign -- leading to instability and loss of identity in long-lived systems. In this work, we propose a capability-centric evolution paradigm for embodied agents. We argue that a robot should maintain a persistent agent as its cognitive identity, while enabling continuous improvement through the evolution of its capabilities. Specifically, we introduce the concept of Embodied Capability Modules (ECMs), which represent modular, versioned units of embodied functionality that can be learned, refined, and composed over time. We present a unified framework in which capability evolution is decoupled from agent identity. Capabilities evolve through a closed-loop process involving task execution, experience collection, model refinement, and module updating, while all executions are governed by a runtime layer that enforces safety and policy constraints. We demonstrate through simulated embodied tasks that capability evolution improves task success rates from 32.4% to 91.3% over 20 iterations, outperforming both agent-modification baselines and established skill-learning methods (SPiRL, SkiMo), while preserving zero policy drift and zero safety violations. Our results suggest that separating agent identity from capability evolution provides a scalable and safe foundation for long-term embodied intelligence.

Related papers

• EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness? [83.21711423118768]
  EVOHARNESSBENCH is a benchmark for evaluating agents under controlled harness evolution.<n>It contains 17 multi-stage harness streams constructed deterministically from verifier-based benchmarks.
  arXiv  Detail & Related papers  (2026-09-03T03:24:02Z)
• EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents [18.945601649519478]
  Self-evolving agents can generate, refine, and reuse skills from past experiences to enable continuous capability evolution.<n>However, autonomous skill evolution introduces a new attack surface in which malicious capabilities are generated, stored, and reused as legitimate skills.<n>In this paper, we define EvoSkill Injection as a threat model targeting the autonomous skill generation and evolution pipeline of self-evolving agents.
  arXiv  Detail & Related papers  (2026-08-31T08:25:03Z)
• 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)
• Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering [50.72456732323037]
  We propose textbfSwarm Skills, a portable specification that extends the Anthropic Skills standard with multi-agent semantics.<n>Swarm Skills turns multi-agent into first-class, distributable assets that consist of roles, execution bounds, and a built-in semantic structure for self-evolution.<n>We show how Swarm Skills achieves zero-adapter cross-agent portability via progressive disclosure, enabling agent teams to self-evolve their coordination strategies without framework lock-in.
  arXiv  Detail & Related papers  (2026-05-11T06:26:58Z)
• Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation [29.927620139561327]
  We show that adapting to new task distributions can progressively degrade previously acquired capabilities across all major evolution channels.<n>We propose emphCapability-Preserving Evolution (CPE), a general stabilization principle that constrains destructive capability drift during continual adaptation.<n>Our findings suggest that stable long-horizon self-evolving agents require not only acquiring new capabilities, but also explicitly preserving previously learned ones.
  arXiv  Detail & Related papers  (2026-05-10T04:20:24Z)
• Self-Evolving Software Agents [0.9281671380673306]
  We propose a BDI-LLM architecture in which an automated evolution module operates alongside the agent's reasoning loop.<n>A prototype evaluated in a dynamic multi-agent environment shows that agents can autonomously discover new goals and generate executable behaviours.
  arXiv  Detail & Related papers  (2026-04-29T23:31:51Z)
• Your Code Agent Can Grow Alongside You with Structured Memory [6.836735626065529]
  We propose MemCoder, a framework designed to enable continual human-AI co-evolution.<n>MemCoder first structures historical human experience to distill latent intent-to-code mappings from past commits.<n>It then employs a self-refinement mechanism driven by verification feedback to correct agent behavior in real-time.
  arXiv  Detail & Related papers  (2026-02-25T06:39:29Z)
• Position: Agentic Evolution is the Path to Evolving LLMs [56.733933092220845]
  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.
  arXiv  Detail & Related papers  (2026-01-30T22:15:58Z)
• 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)
• Logic-Driven Semantic Communication for Resilient Multi-Agent Systems [26.964933264412412]
  6G networks are accelerating autonomy and intelligence in large-scale, decentralized multi-agent systems.<n>This article proposes a formal definition of MAS resilience grounded in two complementary dimensions.<n>We design an agent architecture and develop decentralized algorithms to achieve both epistemic and action resilience.
  arXiv  Detail & Related papers  (2026-01-11T00:54:09Z)
• Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning [84.70211451226835]
  Large Language Model (LLM) Agents are constrained by a dependency on human-curated data.<n>We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data.<n>Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-11-20T05:01:57Z)
• EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle [26.048906477714937]
  Current Large Language Model (LLM) agents show strong performance in tool use, but lack the capability to systematically learn from their own experiences.<n>We introduce EvolveR, a framework designed to enable agent to self-improve through a complete, closed-loop experience lifecycle.<n>We demonstrate the effectiveness of EvolveR on complex multi-hop question-answering benchmarks, where it achieves superior performance over strong agentic baselines.
  arXiv  Detail & Related papers  (2025-10-17T12:03:16Z)
• From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions [70.72279728350763]
  Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems.<n>Unlike static AI models, self-evolving agents embed an autonomous evolution cycle that updates models, tools, and in response to environmental dynamics.<n>This paper presents a comprehensive overview of self-evolving agentic AI, highlighting its layered architecture, life cycle, and key techniques.
  arXiv  Detail & Related papers  (2025-10-07T05:45:25Z)
• 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)

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.