Consistent Plan-Act for Long-Horizon Agentic Tasks
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/Fir-lat/ConPAct
Terminology
Sources
- GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks
- CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments
- Enhancing LLM-Based Agents via Global Planning and Hierarchical Execution
- Qwen3-VL Technical Report
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- DynaWeb: Model-Based Reinforcement Learning of Web Agents
- ContextFlow: Hierarchical Task-State Alignment for Long-Horizon Embodied Agents
- Evaluating Large Language Models Trained on Code
- Training Deep Nets with Sublinear Memory Cost
- lmgame-Bench: How Good are LLMs at Playing Games?
- TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents
- What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment
- Kimi K3: Open Frontier Intelligence
- Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents
- OpenAI GPT-5 System Card
- Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
- Plover: Steering GUI Agents through Plan-Centric Interaction
- CAST: Game Solvers as Turn-Level Teachers for LLM Agents
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