Coding Agent Memory Post-Training II: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via On-Policy Distillation
cs.LG, cs.AI, cs.CL
Submitted: 2026-11-10
Updated: 2026-11-12
Project page: https://liruiluo.github.io/agentmemorygym-v2
Terminology
Sources
- Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation
- SCOPE-OPSD: Fisher-Conditioned Privileged Subspaces for On-Policy Self-Distillation
- MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- SWE-Bench Pro V2: A Cleaner, Harder-to-Game Coding Benchmark
- HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation
- Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory Writing
- PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation
- Understanding the Benefits of Scaffolds through Computational Separations
- Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
- Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation
- Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
- Trajectory-Refined Distillation
- Asymmetric Actor-Critic for Multi-turn LLM Agents
- The Gradient That Top-k Distillation Never Computes
- Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory
- ACM: Agentic Context Management for Long Horizon Tasks
- CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents
- MemOPD: On-Policy Distillation through Memory State Alignment for Long-Horizon Agents
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis