EvoWiki: Incremental State Overwriting and Traceable Question Answering for Cross-Meeting Knowledge Evolution

• URL: http://arxiv.org/abs/2608.23265v1
• Date: Mon, 24 Aug 2026 13:52:17 GMT
• Title: EvoWiki: Incremental State Overwriting and Traceable Question Answering for Cross-Meeting Knowledge Evolution
• Abstract summary: EvoWiki is an incremental question-answering architecture for dynamic long-form text.<n>We present EvoWiki, an incremental question-answering architecture for dynamic long-form text.
• Score: 7.9408412949302525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In long-term collaboration spanning multiple meetings, factual states such as decisions and risks are continually revised, overturned, and replaced. Existing long-context methods typically stack the entire history, while many RAG and structured-memory methods organize knowledge as static or append-only facts and rely on semantic relevance at read time. Without explicit modeling of knowledge lifecycles, these approaches may retain conflicting old and new states simultaneously or discard history, leading to stale retrieval and answers that are difficult to verify. We present EvoWiki, an incremental question-answering architecture for dynamic long-form text. EvoWiki decouples offline incremental construction (BUILD) from online structured reading (READ). BUILD captures the intra-meeting micro-evolution from proposal to decision and uses entity version chains and a fine-grained State-Overwrite Protocol to explicitly distinguish current valid states from superseded history while preserving meeting-level provenance anchors. READ bypasses relevance-based Top-k retrieval and performs deterministic entity addressing, temporal resolution, and cross-entity multi-hop aggregation over the complete Wiki to produce grounded and traceable answers. We further introduce CrossMeet, a high-fidelity bilingual benchmark designed to simulate long-term state evolution, covering factual consistency, temporal reasoning, and cross-meeting multi-hop reasoning. Across six datasets and two reader models, EvoWiki improves macro-average Judge Accuracy over the strongest baselines by 9.72 and 10.00 percentage points, respectively. Human evaluation shows that EvoWiki is more robust and factually faithful under frequent state flips, validating valid-state-oriented reading as a reliable approach to cross-meeting knowledge evolution.

Related papers

• REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering [25.519927761448603]
  REVEAL is a rubric-guided agent framework for long-video question answering.<n>We introduce an adaptive visual-similarity-based preprocessing pipeline that groups visually coherent adjacent frames into natural event units.<n>Built upon this structured memory, REVEAL uses an automatically constructed rubric library to explicitly verify whether retrieved evidence satisfies sufficiency criteria.
  arXiv  Detail & Related papers  (2026-08-09T09:55:42Z)
• TrajWiki: Source-Grounded Memory Trajectories for Long-Horizon Dialogue Agents [17.027152676146592]
  We propose TrajWiki, a trajectory-based memory framework for long-horizon conversational agents.<n>Instead of treating memory as static entries, TrajWiki represents each memory as a source-grounded evolution trajectory.<n>TrajWiki further introduces Memory Wiki, a persistent intermediate layer that incrementally compiles dialogue history into structured and interlinked wiki pages.
  arXiv  Detail & Related papers  (2026-08-02T03:36:03Z)
• TRACE: State-Aware Query Processing over Temporal Evidence Graphs for Conversational Data [15.389000154441986]
  We present TRACE, a query processing framework over temporal evidence graphs for evolving conversational data.<n>TRACE models conversations as a hierarchical graph spanning events, sessions, and topics, enriched with typed temporal, causal, update, and contradiction relations.<n>At query time, TRACE combines vector-based note retrieval with graph-guided evidence search, generating validity-aware support paths and a hybrid context for answer generation.
  arXiv  Detail & Related papers  (2026-07-01T02:28:47Z)
• REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs [17.526686616588794]
  Large Language Models (LLMs) are increasingly expected to interact with users over long time horizons.<n>LLMs cannot retain all past interactions, making long-term memory management essential for storing, updating, and retrieving historical information.<n> REAL constructs long-term conversational memory as a temporal and confidence-aware directed property graph.
  arXiv  Detail & Related papers  (2026-06-09T10:53:10Z)
• SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent [51.274445160155864]
  Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and partial conclusions.<n>Existing approaches address this difficulty by truncating the interaction history, compressing it into shorter surrogates, or retrieving selected parts of it for reuse.<n>We propose State-Adaptive Memory, a standalone framework that consolidates ongoing interaction into compact memory cues while preserving raw trajectory pages for intent-driven recall.
  arXiv  Detail & Related papers  (2026-05-23T08:37:16Z)
• MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems [69.06764269022925]
  We study how current memory-augmented agents perform in realistic, interference-heavy, long-horizon settings.<n> MINTEval is a benchmark featuring long, highly interconnected contexts with frequently updated information.<n>Overall, MINTEval has 15.6k question-answering pairs over long-horizon contexts averaging 138.8k tokens and extending to 1.8M tokens per instance.
  arXiv  Detail & Related papers  (2026-05-18T15:43:35Z)
• Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams [78.9560820155271]
  We evaluate online adaptation over streaming, continually updating knowledge.<n> OAKS comprises two datasets: OAKS-BABI and OAKS-Novel.<n>Both state-of-the-art models and agentic memory systems fail to adapt robustly on OAKS.
  arXiv  Detail & Related papers  (2026-03-08T00:38:39Z)
• AMA: Adaptive Memory via Multi-Agent Collaboration [54.490349689939166]
  We propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities.<n>AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods.
  arXiv  Detail & Related papers  (2026-01-28T08:09:49Z)
• Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation [69.45495166424642]
  We develop a robust and discriminative QA benchmark to measure temporal, causal, and character consistency understanding in narrative documents.<n>We then introduce Entity-Event RAG (E2RAG), a dual-graph framework that keeps separate entity and event subgraphs linked by a bipartite mapping.<n>Across ChronoQA, our approach outperforms state-of-the-art unstructured and KG-based RAG baselines, with notable gains on causal and character consistency queries.
  arXiv  Detail & Related papers  (2025-06-06T10:07:21Z)
• PICASO: Permutation-Invariant Context Composition with State Space Models [98.91198288025117]
  State Space Models (SSMs) offer a promising solution by allowing a database of contexts to be mapped onto fixed-dimensional states.<n>We propose a simple mathematical relation derived from SSM dynamics to compose multiple states into one that efficiently approximates the effect of concatenating raw context tokens.<n>We evaluate our resulting method on WikiText and MSMARCO in both zero-shot and fine-tuned settings, and show that we can match the strongest performing baseline while enjoying on average 5.4x speedup.
  arXiv  Detail & Related papers  (2025-02-24T19:48:00Z)
• 'I Updated the <ref>': The Evolution of References in the English Wikipedia and the Implications for Altmetrics [0.0]
  We present a dataset of the history of all the references (more than 55 million) ever used in the English Wikipedia until June 2019. We have applied a new method for identifying and monitoring references in Wikipedia, so that for each reference we can provide data about associated actions: creation, modifications, deletions, and reinsertions.
  arXiv  Detail & Related papers  (2020-10-06T23:26:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.