Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution

• URL: http://arxiv.org/abs/2606.28971v1
• Date: Sat, 27 Jun 2026 15:21:47 GMT
• Title: Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution
• Abstract summary: Self-Evolving Agentic Image Restoration formulates restoration as a sequential decision-making problem.<n>Inspired by the dual-process theory, SEAR comprises an Intuitive Executor and a Deliberate Planner.<n>Experiments on synthetic and real-world benchmarks demonstrate its strong perceptual and quantitative performance.
• Score: 27.721743933778004
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world image restoration (IR) remains challenging due to complex and coupled degradations. While recent agentic IR frameworks leverage Large Language Models for flexible tool planning, they face two critical limitations. First, from a search scheme perspective, excessive reliance on greedy strategies fails to balance exploration and exploitation. Second, existing agentic systems underutilize information, exhibiting episodic amnesia. To address these challenges, we propose \textbf{Self-Evolving Agentic Image Restoration (SEAR)}, which formulates restoration as a sequential decision-making problem. Inspired by the dual-process theory, SEAR comprises an Intuitive Executor and a Deliberate Planner, respectively following the fast-thinking \textit{System 1} and slow-thinking \textit{System 2} principles. The Deliberate Planner employs Pruning-Aware Monte Carlo Tree Search for long-horizon reasoning, utilizing a hybrid no-reference reward and a Multimodal Large Language Model (MLLM)-based tournament to prevent metric exploitation. Complementarily, the Intuitive Executor leverages a self-evolving episodic memory indexed by degradation-aware state fingerprints. This mechanism distills expensive search trajectories into adaptive expertise, overcoming episodic amnesia while progressively amortizing cold-start exploration costs through memory reuse. Extensive experiments on synthetic and real-world benchmarks demonstrate its strong perceptual and quantitative performance.

Related papers

• NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability [16.584782300163862]
  Large Language Models (LLMs) have been increasingly deployed as autonomous agents in applications such as self-reflection, retrieval-augmented generation, and scientific discovery.<n>This introduces several key challenges: belief state inference, task objective misalignment, and planning under uncertainty.<n>We propose a novel neuro-symbolic fast-slow thinking (NeSyFS) framework for LLM agent, addressing the challenges introduced by partial observability.
  arXiv  Detail & Related papers  (2026-07-31T01:53:41Z)
• Tool-Adaptive LLM Reranker [6.360159778061184]
  TALRanker is a novel framework that formalizes pointwise relevance scoring as an agentic Markov decision process.<n>It achieves state-of-the-art performance across standard and reasoning-intensive retrieval benchmarks.
  arXiv  Detail & Related papers  (2026-07-12T04:04:59Z)
• SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval [74.1918709002557]
  We introduce textbfSGA-MCTS, a framework that casts LLM planning as non-parametric retrieval.<n>Online, a retrieval-augmented agent employs a hybrid symbolic-semantic mechanism to fetch relevant State-Goal-Action atoms.<n>By effectively amortizing the heavy computational cost of search, SGA-MCTS achieves System 2 reasoning depth at System 1 inference speeds, rendering autonomous planning both scalable and real-time feasible.
  arXiv  Detail & Related papers  (2026-04-16T07:22:36Z)
• EpiAgent: An Agent-Centric System for Ancient Inscription Restoration [60.77886293107454]
  EpiAgent is an agent-centric system that formulates inscription restoration as a hierarchical planning problem.<n>EpiAgent achieves superior restoration quality and stronger generalization compared to existing methods.<n>Our work marks an important step toward expert-level agent-driven restoration of cultural heritage.
  arXiv  Detail & Related papers  (2026-04-10T14:37:54Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Improving Coherence and Persistence in Agentic AI for System Optimization [9.443037059325086]
  Engram organizes exploration into a sequence of agents that iteratively design, test, and analyze mechanisms.<n>We find that Engram exhibits superior performance across diverse domains including multi-cloud multicast inference, LLM request routing, and optimizing KV cache reuse in databases with natural language queries.
  arXiv  Detail & Related papers  (2026-03-22T17:04:50Z)
• Agentic Spatio-Temporal Grounding via Collaborative Reasoning [80.83158605034465]
  Temporal Video Grounding aims to retrieve thetemporal tube of a target object or person in a video given a text query.<n>We propose the Agentic Spatio-Temporal Grounder (ASTG) framework for the task of STVG towards an open-world and training-free scenario.<n>Specifically, two specialized agents SRA (Spatial Reasoning Agent) and TRA (Temporal Reasoning Agent) constructed leveraging on modern Multimoal Large Language Models (MLLMs)<n>Experiments on popular benchmarks demonstrate the superiority of the proposed approach where it outperforms existing weakly-supervised and zero-shot approaches by a margin
  arXiv  Detail & Related papers  (2026-02-10T10:16:27Z)
• Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search [10.50683307818034]
  Empirical-MCTS is a dual-loop framework that transforms stateless search into a continuous, non-parametric learning process.<n>We show that Empirical-MCTS significantly outperforms both stateless Monte Carlo Tree Search strategies and standalone experience-driven agents.
  arXiv  Detail & Related papers  (2026-02-04T06:14:55Z)
• OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows [9.617220633655716]
  We present textbfunderlineOmni-textbfunderlineModality textbfunderlineGeneration Agent (textbfOMG-Agent)
  arXiv  Detail & Related papers  (2026-02-04T02:25:40Z)
• RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents [144.5598958575922]
  Re-TRAC is an agentic framework that performs cross-trajectory exploration.<n>We show that Re-TRAC consistently outperforms ReAct by 15-20% on BrowseComp with frontier LLMs.
  arXiv  Detail & Related papers  (2026-02-02T18:58:07Z)
• Self-Consolidation for Self-Evolving Agents [51.94826934403236]
  Large language model (LLM) agents operate as static systems, lacking the ability to evolve through lifelong interaction.<n>We propose a novel self-evolving framework for LLM agents that introduces a complementary evolution mechanism.
  arXiv  Detail & Related papers  (2026-02-02T11:16:07Z)
• 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)

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.