paper-with-me

홈 › Papers

A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation

2026-03-09 · Cong Cao, Jingyao Zhang, Kun Tong arxiv

We propose a Hierarchical Error-Corrective Graph FrameworkforAutonomousAgentswithLLM-BasedActionGeneration(HECG),whichincorporates three core innovations: (1) Multi-Dimensional Transferable Strategy (MDTS): by integrating task quality metrics (Q), confidence/cost metrics (C), reward metrics (R), and LLM-based semantic reasoning scores (LLM-Score), MDTS achieves multi-dimensional alignment between quantitative performance and semantic context, enabling more precise selection of high-quality candidate strate gies and effectively reducing the risk of negative transfer. (2) Error Matrix Classification (EMC): unlike simple confusion matrices or overall performance metrics, EMC provides structured attribution of task failures by categorizing errors into ten types, such as Strategy Errors (Strategy Whe) and Script Parsing Errors (Script-Parsing-Error), and decomposing them according to severity, typical actions, error descriptions, and recoverability. This allows precise analysis of the root causes of task failures, offering clear guidance for subsequent error correction and strategy optimization rather than relying solely on overall success rates or single performance metrics. (3) Causal-Context Graph Retrieval (CCGR): to enhance agent retrieval capabilities in dynamic task environments, we construct graphs from historical states, actions, and event sequences, where nodes store executed actions, next-step actions, execution states, transferable strategies, and other relevant information, and edges represent causal dependencies such as preconditions for transitions between nodes. CCGR identifies subgraphs most relevant to the current task context, effectively capturing structural relationships beyond vector similarity, allowing agents to fully leverage contextual information, accelerate strategy adaptation, and improve execution reliability in complex, multi-step tasks.

📄 PDF Abstract BibTeX arXiv:2603.08388

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ParkingWorld: End-to-End Autonomous Parking Reinforcement Learning from Corrective Experience in 3DGS Simulation

2026-05-24 · Zhengcheng Yu, Changze Li, Haoran Liu, Tong Qin arxiv

Autonomous parking demands precise low-speed maneuvering within narrow, cluttered, and highly constrained environments, where vehicles must navigate tight spaces while avoiding static obstacles and complex geometric boun…

Reinforcement Learning

Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning

2022-04-13 · Ugo Lecerf, Christelle Yemdji-Tchassi, Pietro Michiardi

When learning to act in a stochastic, partially observable environment, an intelligent agent should be prepared to anticipate a change in its belief of the environment state, and be capable of adapting its actions on-the…

Autonomous DrivingAutonomous NavigationAutonomous Vehicles

Learning Sidewalk Autopilot from Multi-Scale Imitation with Corrective Behavior Expansion

2026-03-23 · Honglin He, Yukai Ma, Brad Squicciarini, Wayne Wu 외 arxiv

Sidewalk micromobility is a promising solution for last-mile transportation, but current learning-based control methods struggle in complex urban environments. Imitation learning (IL) learns policies from human demonstra…

Accelerating Hierarchical Sparse Predictive Coding with Hybrid Amortized Inference

2026-06-26 · Kazuhisa Fujita arxiv

Hierarchical predictive coding provides an interpretable framework for perception as error-driven inference in multi-layer generative models, while sparse coding imposes parsimonious latent representations through explic…

McSc: Motion-Corrective Preference Alignment for Video Generation with Self-Critic Hierarchical Reasoning

2025-11-28 · Qiushi Yang, Yingjie Chen, Yuan Yao, Yifang Men 외 arxiv

Text-to-video (T2V) generation has achieved remarkable progress in producing high-quality videos aligned with textual prompts. However, aligning synthesized videos with nuanced human preference remains challenging due to…

Reinforcement LearningVideo Generation