arXiv AI
Jul 24
AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning
arXiv:2607. 21106v1 Announce Type: new Abstract: Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging.
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.
Related stories
arXiv AI
Aug 3
AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction
arXiv:2607. 21106v2 Announce Type: replace Abstract: Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging.
arXiv AI
4d 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
Jul 28
MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents
arXiv:2607. 24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model.
arXiv AI
Jul 28
LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory
arXiv:2607. 22690v1 Announce Type: new Abstract: Long-term memory lets LLM agents reuse past interactions, but raw dialogue histories are verbose and information-sparse.
arXiv AI
Sep 1
AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
AgenticRag‑R1 is a reinforcement‑learning framework that integrates reasoning, retrieval, and memory through a stack and fine‑grained action space. It uses hierarchical action‑aware rewards and an information‑aware trajectory rejection strategy to support long‑horizon learning. Experiments on multi‑hop, open‑domain, and agentic reasoning benchmarks show that AgenticRag‑R1 outperforms strong baselines and produces robust, interpretable, memory‑aware reasoning behaviors.
arXiv Computation and Language
Aug 27
AWM: Answerable Working Memory for Long-Document VQA Agents
The paper introduces AWM, a framework that treats the terminal working memory of long‑document VQA agents as an answerable evidence artifact. It proposes a memory‑only answerability diagnostic and incorporates this signal into the GRPO reward, giving higher advantage to trajectories whose final memory can answer the question alone. Experiments on MMLongBench‑Doc and LongDocURL show that AWM‑GRPO boosts final‑answer accuracy by up to 11.9 points and reduces the rate of correct answers that cannot be supported by memory alone.
arXiv AI
Aug 11
Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards
arXiv:2608. 07531v1 Announce Type: cross Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence.
arXiv AI
Sep 2
Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
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 Machine Learning
4d ago
Learning What to Remember: Long-horizon Counterfactual Memory Optimization
arXiv:2609.37930v1 Announce Type: cross Abstract: Persistent textual memory allows language models to carry information across long interactions, but learning what to remember is fundamentally a cred...
arXiv AI
Jun 18
Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning
arXiv:2606. 18831v1 Announce Type: cross Abstract: Long-context reasoning is an essential capability for large language models, particularly when they are deployed as autonomous agents that must reason over lengthy trajectories.
arXiv AI
Aug 24
Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents
The paper introduces the Weighted Memory Tree (WMT), a hierarchical memory system for large language model agents that organizes execution histories into tasks, subtasks, and actions while assigning each memory a dynamic retention score. Event-based updates and selection-based decay allow WMT to preserve useful information, fold completed trajectories, suppress low-utility content, and retain access to folded context. Experiments on GAIA-Text with Qwen3-8B, Gemma 4 E4B, and Llama-3.1-8B show that WMT improves accuracy by an average of 9.97 percentage points and reduces prompt-token usage by 32.8%, while also limiting the persistence of unreliable information.