Learning What to Remember: Long-horizon Counterfactual Memory Optimization

arXiv:2609.37930 · cs.CL, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Credit assignment — 14× in this paper · explained in 3 episodes
• GRPO — 9× in this paper · explained in 6 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Downstream Tasks — 5× in this paper · explained in 2 episodes
• Memory Gain Policy Optimization — 5× in this paper
• Ablation — 4× in this paper · explained in 1 episode
• Accuracy — 4× in this paper · explained in 1 episode
• Adaptation — 4× in this paper · explained in 1 episode
• Clustering — 4× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 4× in this paper
• Reward Shaping — 4× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• KV cache — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Exponential Moving Average — 1× in this paper
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Phi-4 Technical Report
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• The Llama 3 Herd of Models
• Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Decoding the Legalese: A Scalable and Quantitative Framework for Analyzing Corporate Privacy Policies
• Mem-{\alpha}: Learning Memory Construction via Reinforcement Learning
• HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents
• Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering