# ExperienceIndex: Artifact-Grounded Memory

arXiv: https://arxiv.org/abs/2610.10091 · HTML: https://mlsanity.com/paper/2610.10091/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite](https://mlsanity.com/paper/2510.21652/) (2025)
- [Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://mlsanity.com/paper/2606.15007/) (2026)
- [REMem: Reasoning with Episodic Memory in Language Agent](https://mlsanity.com/paper/2602.13530/) (2026)
- [EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline](https://mlsanity.com/paper/2504.03598/) (2025)
- [FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents](https://mlsanity.com/paper/2504.13128/) (2025)
- [Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation](https://mlsanity.com/paper/2505.14398/) (2025)
- [KARL: Knowledge Agents via Reinforcement Learning](https://mlsanity.com/paper/2603.05218/) (2026)
- [Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit](https://mlsanity.com/paper/2607.13095/) (2026)
- [PAR2-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering](https://mlsanity.com/paper/2603.29085/) (2026)

## Abstract (arXiv)

Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literature). As humans interact with these corpora, they naturally accumulate experiential knowledge about artifacts, enabling them to quickly identify the complete set of relevant artifacts for each new task. However, existing AI agents lack appropriate memory solutions to build or reuse such artifact-grounded experience, leading to lower answer quality and higher online cost. Existing memory solutions extract and reuse information from prior task-solving traces, but they primarily focus on user preferences, factual attributes, or abstract reasoning patterns rather than persistent artifact-specific knowledge. We introduce ExperienceIndex, a novel experience layer for AI agents that captures and reuses knowledge about artifacts based on prior reasoning traces. ExperienceIndex stores two complementary forms of experience: (i) single-artifact experiences that summarize an artifact's contribution to prior tasks and (ii) artifact-pair experiences that encode structural relationships discovered during past reasoning. Integrated as lightweight middleware, ExperienceIndex uses an experience retrieval mechanism to guide agents toward the complete set of relevant artifacts for new tasks, improving both answer quality and efficiency. Across diverse corpora and agentic solutions with different search frameworks, ExperienceIndex delivers consistent gains, raising answer quality by up to 11.0 points and reducing online dollar cost by up to 50.5%. We further demonstrate two benefits: (i) cross-task generalization, where experiences accumulated from text-to-SQL tasks transfer to factoid QA tasks over the same artifact corpus, and (ii) teacher-student learning, where experiences from a stronger model enable a weaker model to reach comparable performance.