Coding Agent Memory Post-training: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via Reinforcement Learning
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-28
Updated: 2026-09-30
Code: https://github.com/letta-ai/letta-code
Project page: https://liruiluo.github.io/agentmemorygym
Terminology
Sources
- PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
- RollArt: Disaggregated Multi-Task Agentic RL Training at Scale
- Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
- ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay
- AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation
- ComboShoppingBench: Evaluating LLM Agents for Budget-Constrained Basket Shopping with Coupons
- Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs
- ACM: Agentic Context Management for Long Horizon Tasks
- Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning
- CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents
- MemGPT: Towards LLMs as Operating Systems
- Proximal Policy Optimization Algorithms
- Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
- ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL
- Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
- Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
- Learning Agent-Compatible Context Management for Long-Horizon Tasks
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks