arXiv Machine Learning
Learning What to Remember: Long-horizon Counterfactual Memory Optimization
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
3d ago
CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory
CoEM introduces a Commit-on-Evidence Memory system that learns when to compress source evidence into compact memory facts while preserving potentially useful excerpts verbatim in a pending set. The system uses a learned policy to decide whether to promote, retain, or discard each pending excerpt as new context arrives, and a frozen verifier ensures only supported facts are committed. Reinforcement learning trains this policy with step-level evidence rewards and final answer rewards, leading to consistent improvements in long-context reasoning, achieving 10.4–11.4 F1 points over the strongest baseline on 6,400-document inputs.
arXiv AI
Sep 3
AdaMem: Learning What to Remember with Adaptive Memory Policies for Personalized Agents
AdaMem introduces adaptive memory policies that allow personalized agents to decide what information to write into long‑term memory based on user preferences for each interaction context. Each policy is updated from periodic feedback and controls subsequent memory writing, aiming to improve relevance and reduce unnecessary memory persistence. In experiments on AdaMem‑Bench, AdaMem raises QA accuracy from 80.0% to 84.35% while cutting persistent memory by 9.27%, though models still struggle to execute policies reliably.
arXiv AI
Jun 3
InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain
arXiv:2606. 03329v1 Announce Type: new Abstract: Long-context tasks require LLMs to identify and preserve answer-relevant information from large contexts.
arXiv Machine Learning
Aug 27
From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection
The paper introduces Golden-GRPO Injection (GRIN), a three-stage self‑learning framework that uses a mixed‑policy reinforcement learning algorithm to inject knowledge into large language models. GRIN injects a golden answer to provide learning signals even when on‑policy rollouts fail on novel facts, and is evaluated on two new document‑level benchmarks—Blank and Counter—that test novel acquisition and counterfactual overwrite. Experiments show that mixed‑policy RL enables knowledge absorption beyond what supervised fine‑tuning can achieve, with GRIN outperforming SFT and other RL baselines on harder question types while matching them on basic fact recall.
arXiv Machine Learning
Sep 10
Continual Learning Mechanisms Compose for Long-Horizon Memorization
arXiv:2609.06986v1 Announce Type: new Abstract: Language models may need to internalize information that arrives over time and retain it through many subsequent updates. To study this challenge, we i...
arXiv AI
Aug 5
Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents
arXiv:2608. 03137v1 Announce Type: new Abstract: Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon interaction.