CIPO: Counterfactual Imagination Policy Optimization for Adaptive Tool Granularity Selection
cs.AI
Submitted: 2026-10-04
Updated: 2026-10-04
Sources
- Optimizing Agentic Workflows using Meta-tools
- Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making
- FireAct: Toward Language Agent Fine-tuning
- GTool: Graph Enhanced Tool Planning with Large Language Model
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
- Memp: Exploring Agent Procedural Memory
- The Llama 3 Herd of Models
- TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
- Qwen2.5-Coder Technical Report
- SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
- MTDrive: Multi-turn Interactive Reinforcement Learning for Autonomous Driving
- PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
- AutoFlow: Automated Workflow Generation for Large Language Model Agents
- CaRT: Teaching LLM Agents to Know When They Know Enough
- AgentBench: Evaluating LLMs as Agents
- SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
- Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
- WebGPT: Browser-assisted question-answering with human feedback
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