# Reconcile Once, Write Anytime: A Trust-Tiered Librarian and a Multi-Agent Writer for Drift-Free, Point-in-Time Research

arXiv: https://arxiv.org/abs/2608.12984 · HTML: https://mlsanity.com/paper/2608.12984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [A Dataset for Answering Time-Sensitive Questions](https://mlsanity.com/paper/2108.06314/) (2021)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models](https://mlsanity.com/paper/2205.11388/) (2022)
- [FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering](https://mlsanity.com/paper/2601.06992/) (2026)
- [Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution](https://mlsanity.com/paper/2603.11445/) (2026)
- [REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry](https://mlsanity.com/paper/2603.03018/) (2026)
- [FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting](https://mlsanity.com/paper/2603.19254/) (2026)

## Abstract (arXiv)

Long-form research reports generated by large language models drift, contradict themselves, and lose provenance: the same metric appears with different values, and rumor is quoted as confidently as an audited filing. We present a two-tier agentic system that separates a maintained, point-in-time knowledge library from report writing. A deterministic "librarian" ingests timestamped sources into a trust-tiered ontology, layering evidence cards, an authoritative metric ledger, and a claim graph into an always-current source of truth, not per-query RAG over raw chunks. A portable multi-agent "writer" runtime then composes a contradiction-free, evidence-grounded report at any knowledge cutoff T, reading only evidence with as_of <= T (no look-ahead); red-team verdicts flow back into the librarian. We evaluate on a self-collected, public corpus of 6,130 sources yielding 555,926 evidence cards (SEC EDGAR filings across 295 issuers and 11 sectors, U.S. Bureau of Labor Statistics releases, and Wikipedia). From the one library we compose four point-in-time reports on distinct theses and run eight reproducible experiments, whose headline metrics come from a deterministic quality-control gate, itself validated by defect-injection meta-evaluation at recall 1.0 and precision 1.0. A shared metric ledger removes 6,845 cross-section contradictions to zero. Tier-first selection is correct on 22/22 gold cases where a popularity-first baseline scores only 9/22; trust tiering leaks zero media-sourced numbers, and no government statistic displaces a company's own filing. A red-team refutation propagates back and self-corrects a later run with zero manual edits. Replay exhibits zero look-ahead violations across seven cutoffs while the library grows from 235,373 to 555,312 cards. Difficulty-tiered model routing exceeds the all-Opus quality ceiling while running 3.7x faster than serial.