---
title: "LMLineage: Content Lineage and Context... | SI Paper Desk"
url: https://thesimind.si/papers/2611.22511/
description: "LMLineage traces each sentence an SI agent writes back to the input passages that support it, without opening the model, and uses that trail to trim stale..."
---

Paper of the Day · November 19, 2026

# LMLineage: Content Lineage and Context Governance for LLM Agents

LMLineage traces each sentence an SI agent writes back to the input passages that support it, without opening the model, and uses that trail to trim stale context.

Wei Hou, Jingxin Geng, Xin Chen and 1 more · Submitted November 17, 2026 · arXiv 2611.22511v1 · cs.AI

[Read the paper on arXiv](https://arxiv.org/abs/2611.22511) · [The PDF](https://arxiv.org/pdf/2611.22511) · [The day's 12](https://thesimind.si/papers/day/2026-11-19/)

## What they found

The authors built LMLineage, a system that sits outside the model. It links every output sentence of an agent session to the input passages that support it, with confidence scores. It needs no access to model internals and no extra model runs. They tested it on 71 hand-labeled sentences from 10 Chinese web question-answering cases, plus 90 turns of multi-turn sessions across three generator models. Matching small windows of text by embedding similarity worked far better than matching whole documents or exact words. A fast greedy-window method was faster and more accurate on average than exhaustive line matching. Each turn took about 1s on a single GPU, even as context grew to 40 turns. Their drift detector, which finds input documents the agent has stopped using so they can be compacted, made no false compactions (0%). Its recall was limited by how accurate the attribution was.

## Why it matters

SI agents pull in many documents and instructions over long sessions, and it is hard to tell which source shaped which statement. A cheap, model-agnostic way to trace this could help people audit agent answers. It could also help keep context short without summarizing everything, since user instructions are kept word for word. The test sets are small, and the abstract does not say how well this holds up outside them.

## How it changes the race

This is an incremental, practical tooling advance. It could lower the cost of running long agent sessions and of auditing them, because it works on closed models without extra inference. It does not change model capability itself.

## Safety and control

The system gives a way to trace which inputs support an agent's output, which could help with incident tracing and cleaning memory, as the authors' case study describes. Attribution shows which text supports a sentence, not why the model said it, and the abstract reports that drift detection recall depends on attribution accuracy.

### The abstract, by the authors

Interpretability for AI agents should not be confined to understanding the model's internal weights. It must also cover the agent's reasoning and decision-making process over multi-source context. We present LMLineage, an out-of-band system that attributes every output sentence of an agent session to its supporting input spans with calibrated confidences, without requiring white-box access to the model or any additional inference passes. On top of the lineage metadata, we build concept-drift micro compaction: instead of waiting for the context-length limit and summarizing everything, the system detects when previously used input documents have stopped being referenced ("drifted") and surgically compacts only those, preserving user instructions verbatim. We evaluate on a multi-tier corpus: 71 gold annotated sentences from 10 Chinese web-QA cases, plus 90 turns of independently collected multi-turn sessions across three generator models (gpt-4o-mini, qwen3.8-27b, deepseek-v4-flash). Results show that (i) window-level embedding similarity is far better aligned with LLM paraphrasing than whole document or lexical matching; (ii) the greedy-window fast path is both faster and more accurate on average than exhaustive line-matching (a multiple-comparisons bias in the latter inflates web recall at the cost of overall accuracy); (iii) per-turn attribution completes in 1s on a single GPU, remaining stable as context accumulates to 40 turns; and (iv) concept-drift detection is conservative (0% false compaction) with recall bounded by attribution accuracy. We further describe the concept-drift micro compaction design and an interactive incident-tracing/memory-cleaning case study. A companion patent application covers the lineage construction method.

Quoted from arXiv:2611.22511. The research and its words belong to its authors.

Desk score **84** out of 100

Why it was picked

- Agents (in the title)
- Policy (in the title)
- Interpretability
- Reasoning
- Compute
- Language models (in the title)
- Cross-listed in 2 fields

Topics

- [Interpretability](https://thesimind.si/papers/?tag=interpretability)
- [Agents](https://thesimind.si/papers/?tag=agents)
- [Memory](https://thesimind.si/papers/?tag=memory)
- [Evals](https://thesimind.si/papers/?tag=evals)
- [Efficiency](https://thesimind.si/papers/?tag=efficiency)
- [Language models](https://thesimind.si/papers/?tag=language-models)

**arXiv ID:** 2611.22511v1
**Submitted:** November 17, 2026
**Fields:** cs.AI (Artificial Intelligence), cs.CL (Computation and Language)
**Level:** Intermediate

Fingerprint, SHA-256

`28c8c573b23ff2489ae3794016cdd295c4a845fe39e0c0ef6c83392f99ead18a`

On Solana: [Proof of Mind seal, 3rBYfi...QvEH](https://solscan.io/tx/3rBYfiFP3PxcUbtJzCwpcVq5MngquU5iAtJFeiP7PFVgnsuoTjwwJPjNDYgKxQzUnVq5keQT2KEgX46YTdHqQvEH)

### The exact text fingerprinted

{"arxiv":"2611.22511","version":1,"title":"LMLineage: Content Lineage and Context Governance for LLM Agents","authors":["Wei Hou","Jingxin Geng","Xin Chen","Zheqing Jiang"],"day":"2026-11-19","rank":1,"score":84,"status":"written","summary":{"takeaway":"LMLineage traces each sentence an SI agent writes back to the input passages that support it, without opening the model, and uses that trail to trim stale context.","found":"The authors built LMLineage, a system that sits outside the model. It links every output sentence of an agent session to the input passages that support it, with confidence scores. It needs no access to model internals and no extra model runs. They tested it on 71 hand-labeled sentences from 10 Chinese web question-answering cases, plus 90 turns of multi-turn sessions across three generator models. Matching small windows of text by embedding similarity worked far better than matching whole documents or exact words. A fast greedy-window method was faster and more accurate on average than exhaustive line matching. Each turn took about 1s on a single GPU, even as context grew to 40 turns. Their drift detector, which finds input documents the agent has stopped using so they can be compacted, made no false compactions (0%). Its recall was limited by how accurate the attribution was.","matters":"SI agents pull in many documents and instructions over long sessions, and it is hard to tell which source shaped which statement. A cheap, model-agnostic way to trace this could help people audit agent answers. It could also help keep context short without summarizing everything, since user instructions are kept word for word. The test sets are small, and the abstract does not say how well this holds up outside them.","race":"This is an incremental, practical tooling advance. It could lower the cost of running long agent sessions and of auditing them, because it works on closed models without extra inference. It does not change model capability itself.","safety":"The system gives a way to trace which inputs support an agent's output, which could help with incident tracing and cleaning memory, as the authors' case study describes. Attribution shows which text supports a sentence, not why the model said it, and the abstract reports that drift detection recall depends on attribution accuracy.","level":"intermediate","tags":["interpretability","agents","memory","evals","efficiency","language-models"]}}

[Check it on Verify a thought](https://thesimind.si/proof-of-mind/)

## The authors

Wei Hou, Jingxin Geng, Xin Chen, Zheqing Jiang

Credit for this research belongs to its authors. SI MIND's page is a plain-English reading of their abstract on arXiv, not a review of the full paper.

Related on the desk

## More papers on these topics

[Nov 10, 2026 · Number 3PACE: Keeping the Right Tokens in the KV Cache Is Not Enough for Long-Horizon LLM AgentsKeeping the needed tokens in a SI agent's memory cache is not enough. PACE also renumbers their positions so they stay reachable, and it holds accuracy in sessions of up to 2M tokens.AgentsEfficiencyMemory](https://thesimind.si/papers/2611.10240/) · [Nov 18, 2026 · Paper of the DayGRACE: Parallel Best-of-N Multi-Agent Analysis of Closed-Form Questions over Dataframes with Guardrail Selection and Adaptive RetryGRACE runs several SI agents in parallel on spreadsheet-style questions, judges their executed work instead of voting, and can reject all answers and retry, lifting answer match from 39% to 71% on one benchmark.AgentsMulti-agent systemsCode](https://thesimind.si/papers/2611.20983/) · [Nov 19, 2026 · Number 2Runtime Verification of Multiple Natural Language Criteria for Agent GovernanceThe authors built VFM, a small verifier that checks an SI agent's output against many written rules at once and says which are met, broken, or not relevant.SafetyAgentsEvals](https://thesimind.si/papers/2611.23074/)

[All 12 for Nov 19, 2026](https://thesimind.si/papers/day/2026-11-19/) · [Number 2](https://thesimind.si/papers/2611.23074/)
