# EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents

arXiv: https://arxiv.org/abs/2606.05894 · HTML: https://mlsanity.com/paper/2606.05894/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 32 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 29 of 29)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [Document Expansion by Query Prediction](https://mlsanity.com/paper/1904.08375/) (2019)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [Fine-tune BERT for Extractive Summarization](https://mlsanity.com/paper/1903.10318/) (2019)
- [AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents](https://mlsanity.com/paper/2407.04363/) (2024)
- [MEMORYLLM: Towards Self-Updatable Large Language Models](https://mlsanity.com/paper/2402.04624/) (2024)
- [Mem-α: Learning Memory Construction via Reinforcement Learning](https://mlsanity.com/paper/2509.25911/) (2025)
- [What Deserves Memory: Adaptive Memory Distillation for LLM Agents](https://mlsanity.com/paper/2508.03341/) (2025)
- [BanditSum: Extractive Summarization as a Contextual Bandit](https://mlsanity.com/paper/1809.09672/) (2018)
- [Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents](https://mlsanity.com/paper/2509.23040/) (2025)
- [Beyond Static Summarization: Proactive Memory Extraction for LLM Agents](https://mlsanity.com/paper/2601.04463/) (2026)
- [From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents](https://mlsanity.com/paper/2602.17913/) (2026)
- [AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation](https://mlsanity.com/paper/2601.08323/) (2026)
- [Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory](https://mlsanity.com/paper/2602.06025/) (2026)
- [CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.05467/) (2026)

## Built on by (most cited first, 6 of 6)

- [LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation](https://mlsanity.com/paper/2608.12990/) (2026)
- [When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model](https://mlsanity.com/paper/2609.34227/) (2026)
- [What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory](https://mlsanity.com/paper/2609.08279/) (2026)
- [RoutePrism: Tracing Construction Order Effects in Agent Memory](https://mlsanity.com/paper/2609.34160/) (2026)
- [LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation](https://mlsanity.com/paper/2609.39740/) (2026)
- [MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories](https://mlsanity.com/paper/2609.40195/) (2026)

## Abstract (arXiv)

Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the system must return to larger portions of the raw history. We study budgeted evidence survival: before the query is known, which source evidence should be retained so that it remains recoverable and usable under a fixed retained source-evidence token budget? We instantiate this setting as Budgeted Pre-Query Retention, where memory is written during ingestion and later read without access to the full raw stream. We introduce EMBER, a learned retention policy that constructs a compact, source-backed evidence state. EMBER stores evidence capsules: verbatim source excerpts paired with retrieval keys and update metadata, preserving both grounding and read-time access. Post-query outcome feedback trains the writer to preserve evidence across the ingestion-retrieval-answer chain. On LongMemEval-RR, our LongMemEval-derived retained-evidence protocol, EMBER-14B reaches 0.3017 F1 at the 8192-token retained-evidence comparison point, compared with 0.1765 for the strongest non-EMBER budgeted baseline. Across retained source-evidence budgets, EMBER improves F1, Retain-Recall, and Read-Recall, indicating that long-horizon memory depends on retaining evidence within the budget rather than rereading larger histories.