# AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction

arXiv: https://arxiv.org/abs/2607.21106 · HTML: https://mlsanity.com/paper/2607.21106/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents](https://mlsanity.com/paper/2506.15841/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [ContextCite: Attributing Model Generation to Context](https://mlsanity.com/paper/2409.00729/) (2024)
- [Hindsight Credit Assignment for Long-Horizon LLM Agents](https://mlsanity.com/paper/2603.08754/) (2026)
- [General Agentic Memory Via Deep Research](https://mlsanity.com/paper/2511.18423/) (2025)
- [Adaptive Memory Admission Control for LLM Agents](https://mlsanity.com/paper/2603.04549/) (2026)
- [Mem-T: Densifying Rewards for Long-Horizon Memory Agents](https://mlsanity.com/paper/2601.23014/) (2026)
- [Are We Ready For An Agent-Native Memory System?](https://mlsanity.com/paper/2606.24775/) (2026)
- [MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards](https://mlsanity.com/paper/2601.05488/) (2026)
- [InfMem: Learning System-2 Memory Control for Long-Context Agent](https://mlsanity.com/paper/2602.02704/) (2026)
- [Tracing Agentic Failure from the Flow of Success](https://mlsanity.com/paper/2607.12747/) (2026)
- [Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs](https://mlsanity.com/paper/2602.01914/) (2026)
- [LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning](https://mlsanity.com/paper/2607.13501/) (2026)
- [LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory](https://mlsanity.com/paper/2607.22690/) (2026)
- [Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt Optimization](https://mlsanity.com/paper/2605.30227/) (2026)

## Built on by (most cited first, 5 of 5)

- [Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence](https://mlsanity.com/paper/2608.12743/) (2026)
- [Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit](https://mlsanity.com/paper/2608.29605/) (2026)
- [RoutePrism: Tracing Construction Order Effects in Agent Memory](https://mlsanity.com/paper/2609.34160/) (2026)
- [ReplayLens: Auditing Agents' Use of Outcomes](https://mlsanity.com/paper/2609.34177/) (2026)
- [When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents](https://mlsanity.com/paper/2610.19910/) (2026)

## Abstract (arXiv)

Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract, store, update, compress, or discard as interactions accumulate. Heuristic memory methods rely on subjective, task-specific rules, which can misalign with downstream objectives and limit cross-task adaptability. RL-based methods, by contrast, learn from task feedback but mainly use outcome- or module-level rewards. These coarse signals indicate task success but cannot identify which intermediate memory contents support the final answer, creating a fine-grained credit-assignment bottleneck. However, constructing such process feedback is prohibitively difficult because intermediate memory decisions lack unique ground-truth targets, while the appropriate credit varies with the agent's uncertain reasoning trajectory and therefore cannot be specified in advance. We propose AttriMem, an attribution-guided process-feedback framework for learning memory-construction policies with RL. AttriMem augments the global outcome reward with local rewards derived from token-level contributions to the final answer. Experiments on long-horizon dialogue question answering show that AttriMem outperforms retrieval-based, heuristic, and RL-based baselines, generalizes across benchmarks and answer models, stabilizes RL optimization.