arXiv:2605. 22142v2 Announce Type: replace-cross Abstract: Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations.
arXiv:2607. 18368v1 Announce Type: new Abstract: Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time.
The paper introduces the Unified Memory Agent (UMA), a system that builds a query‑agnostic external memory from a data stream and reuses it across multiple question‑answering sessions. UMA employs a single policy to manage a structured Memory Bank via CRUD operations and uses Task‑Stratified GRPO to supervise memory maintenance based on QA trajectory rewards. The authors also present Ledger‑QA, a benchmark for long‑horizon state tracking, and demonstrate that UMA outperforms other methods on test‑time learning and accurate‑retrieval tasks, with UMA‑Specialist further improving performance after task adaptation.
arXiv:2607. 20553v1 Announce Type: new Abstract: Memory Manager models are pivotal in agent systems.
DeepRefine is a reinforcement learning framework that improves the quality of pre‑constructed structured knowledge bases—such as knowledge graphs or LLM‑Wikis—by engaging in multi‑turn interactions with the base. It performs abductive diagnosis to locate defects, then applies targeted refinement actions to incrementally update the knowledge base. The system uses a Gain‑Beyond‑Draft reward to train its refinement policy end‑to‑end, achieving consistent downstream performance gains over strong baselines.
arXiv:2606. 04492v1 Announce Type: new Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) frequently suffers from severe reward sparsity and exploration bottlenecks.
arXiv:2604. 01577v3 Announce Type: replace-cross Abstract: We study out of distribution generalization in streaming tasks where models are trained on short sequences but must operate over much longer, unknown horizons under bounded memory.
arXiv:2511. 03836v2 Announce Type: replace Abstract: Deep Q-Networks (DQNs) estimate future returns by learning from transitions sampled from a replay buffer.
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
arXiv:2610.00592v1 Announce Type: cross Abstract: In partially observable reinforcement learning (RL), a later observation can make stored information obsolete or change what it implies for the next...
arXiv:2602. 10238v2 Announce Type: replace-cross Abstract: The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache.
arXiv:2603. 11395v3 Announce Type: replace-cross Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future tasks.
The paper introduces BRIDGE, a bilevel optimization framework that jointly trains a large language model (LLM) and a retriever for agentic reinforcement learning (ARL). It demonstrates that adapting the retriever before the policy yields better rewards, and that BRIDGE outperforms existing methods on seven open‑domain QA benchmarks and medical QA tasks, achieving significant gains in accuracy and reasoning quality.