Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution
cs.AI, cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Project page: https://subbareddy248.github.io/projects/declaration-gap-site/1
Sources
- ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning
- What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment
- Aegis: Automated Error Generation and Attribution for Multi-Agent Systems
- Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
- LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
- AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- WebCanvas: Benchmarking Web Agents in Online Environments
- Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
- AdaJEPA: An Adaptive Latent World Model
- Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning
- ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
- AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol
- Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems