TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery
cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Terminology
Sources
- Before Parc Ferm'e: RL-Time Pruning for Efficient Embodied LLMs in Autonomous Driving
- Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction
- Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training
- Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
- TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
- SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
- Qwen3 Technical Report
- ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
- TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks