LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents

Xingjun Wang; Gongsheng Li; Qi Fan; Yunlin Mao; Luyan Su; Yingda Chen

cs.CLAug 17, 2026

LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents

Authors: Xingjun Wang, Gongsheng Li, Qi Fan, Yunlin Mao, Luyan Su, Yingda Chen

Organizations: ModelScope Team, Alibaba Group Hangzhou, China

Abstract

LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent. Existing retrieval-augmented approaches pre-materialize evidence via fixed chunking, embeddings, or persistent indexes: effective for lookup, yet costly, stale-prone, and committed to a granularity before the query is known. We formulate in-context search as Budgeted Evidence Localization over a latent evidence space induced by dynamic raw documents and propose LENS (Latent Evidence Exploration and Search), an index-free framework. Instead of pre-materializing the evidence space, LENS maintains a query-conditioned belief over candidate units, iteratively selecting candidates via complementary lexical, local, and exploratory proposal policies, updating the belief via an LLM relevance oracle, and narrowing toward high-posterior regions under a controllable budget. Evidence is consolidated into compact, source-grounded regions of interest and compressed into self-organizing knowledge clusters reused across related queries. On a controlled 500-question evaluation with matched corpus snapshots, LENS reaches 62.4% exact match and 84.8% evidence recall vs. 65.2% exact match but 50.4% evidence recall for a ReAct-style baseline. Across scales, LENS gives the strongest supporting-fact localization and answer grounding. On a fixed 150-question fullwiki subset over the raw Wikipedia dump with zero indexing, LENS and ReAct are nearly tied in official answer quality (43.3% vs. 42.7% EM), with LENS grounding more answers in retrieved evidence (84.0% vs. 70.7%). A no-retrieval Closed-Book reference highlights the contribution of model memory. LENS is query-ready after corpus changes, needs no preprocessing or persistent index, and preserves source-grounded evidence localization throughout.

Figures & tables

Figure 1: Overall LENS framework. LENS forms a query-conditioned prior over candidate evidence regions, runs a budget-constrained propose–observe–update loop, and consolidates selected regions into a compact source-grounded evidence set for answer synthesis. It never pre-materializes a persistent index over the raw-document collection.

Snapshot	Samples	Articles	Evidence	Background
$D_{125}$	125	5,416	250	4,062
$D_{250}$	250	10,808	500	8,106
$D_{500}$	500	21,424	996	16,068
System ( $D_{500}$ )	Ready	Rebuild	Index(s)	Storage
LENS	yes	no	0.0	0
ReAct	yes	no	0.0	0

Table 1: Snapshot construction and lifecycle audit. The upper block reports deterministic

D_{n}

corpus sizes; the lower block reports

D_{500}

query readiness, rebuild requirement, index time, and index storage.

System	EM	F1	Ev.Rec	Ground
ReAct Search	65.2	78.9	50.4	71.8
LENS	62.4	76.9	84.8	96.8
Hybrid-RAG	38.4	51.1	80.8	92.2
BM25-RAG	28.8	42.3	71.8	95.8
Closed-Book	35.2	47.0	0.0	0.0

Table 2: Controlled evaluation on

D_{500}

(%,

n

=500). EM/F1 are official answer metrics; Ev.Rec is supporting-fact document recall; Ground is the percentage of answers traceable to retrieved evidence.

System	EM	F1	Ev.Rec	Ground
LENS	43.3	57.5	45.0	84.0
ReAct Search	42.7	57.3	50.4	70.7
Closed-Book	38.7	49.7	0.0	0.0

Table 3: Open-domain fullwiki results (%,

n

=150, fixed sample IDs). LENS and ReAct search the raw Wikipedia dump (15,517 shards) with zero indexing; Closed-Book reads no corpus.

System	$D_{125}$	$D_{250}$	$D_{500}$
LENS	89.1	85.9	84.8
Hybrid-RAG	81.3	77.8	80.8
BM25-RAG	71.6	71.1	71.8
ReAct Search	46.1	47.9	50.4
Closed-Book	0.0	0.0	0.0

Table 4: Evidence recall (%) across controlled evaluation scales. LENS consistently provides the strongest supporting-fact localization, while Closed-Book has no evidence trace by design.

System	Fresh	Stale	$\Delta$	Fresh	Stale	$\Delta$
	Exact Match (%)			Evidence Recall (%)
BM25-RAG	30.4	2.4	$-28.0$	70.1	0.0	$-70.1$
Hybrid-RAG	42.4	13.6	$-28.8$	75.1	5.5	$-69.6$
ReAct Search	72.0	72.8	$+0.8$	54.1	48.3	$-5.7$
LENS	69.6	67.2	$-2.4$	84.7	83.9	$-0.8$

Table 5: Staleness robustness under corpus expansion (

D_{125}\to D_{250}

\Delta n=125

). Index-heavy systems reuse an index built on

D_{125}

while answering newly added

D_{250}

questions; index-free systems query the updated corpus directly. Negative gaps indicate stale degradation; the table measures freshness/lifecycle robustness rather than fresh-corpus answer quality.

Configuration	EM	F1	Ev.Rec	Ground
LENS (Full)	43.3	57.5	45.0	84.0
w/o Multi-signal Prior	43.3	55.9	45.4	85.3
w/o Sequential Exploration	38.0	50.9	31.0	82.0

Table 6: Ablation study on the fullwiki evaluation (

n

=150 fixed sample IDs). Ev.Rec is supporting-fact document recall; Ground is the percentage of answers traceable to retrieved evidence.

In-Context Retrieval

In-context retrieval studies how language models find and use relevant facts, examples, or documents supplied within their active context.

See all 29 papers

Aug 7, 2026

DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding

Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-round memory. Mainstream single-round methods commit to a fixed top-

k

page set at the outset and struggle to recover from early retrieval errors; recent iterative approaches allow multi-round evidence acquisition, but they do not investigate the propagation mechanism of cross-round states, making it difficult to track the dynamic changes in page relevance. To address these limitations, we propose DocMemo, a memory-guided framework that formulates long-document reasoning as dynamic evidence exploration. DocMemo maintains a tri-level retrieval state consisting of Document Schema Memory, Page Belief Memory, and Question Episodic Memory, which respectively capture structural priors, dynamic relevance estimation, and query-specific reasoning trajectories. During reasoning, DocMemo continuously refines cross-round page selection through Bayesian page belief updating with Thompson sampling, spatial proximity propagation, and structure-aware adaptive-granularity evidence access, while supplementing page-level evidence with fine-grained visual regions. Experiments on 3 benchmarks show that DocMemo achieves state-of-the-art performance and validate the efficacy of structured memory and dynamic page belief updating. Code is available at https://github.com/Harrygof/DocMemo.

Hanshu Yao, Janfeng Zhong, Niu Lian +1

1Harbin Institute of Technology, Shenzhen · 2Tsinghua Shenzhen International Graduate School, Tsinghua University

Multimodal Memory Document QA Visual Document Retrieval Evidence Retrieval Multimodal Learning

Ask PDF

Oct 20, 2026

Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAG

Scanning every passage in a long document seems thorough, but does it preserve more useful evidence or produce better answers? We compare 11 retrieval configurations spanning lexical and dense search, hybrid reranking, and full-document scanning with Jev, OpenAI Decisions, and Cloudflare Clef. Our evaluation uses 396 QASPER questions and 80 questions from eight complete textbooks, with common passages, a five-passage limit, and a fixed answer generator. On books, Hybrid + Jev achieves the highest observed evidence coverage (94.1%), compared with 88.7% for Jev full scan and 81.3% for OpenAI dense retrieval. Full scans examine every passage initially, yet later reduction steps can discard relevant evidence. Higher evidence coverage also does not consistently produce better answers: Hybrid + Decisions achieves the highest observed book Answer Accuracy among retrieval methods (0.892), despite recovering less reference evidence. Full scanning incurs substantially higher latency on books under the tested deployments, while reusable dense retrieval has lower projected API cost than paid decision-based methods as queries accumulate. Most QASPER articles already fit within the hybrid candidate pool, limiting the benefit of scanning. These results highlight evidence retention, answer quality, and reuse cost as complementary criteria for choosing a long-document retrieval strategy.

Juan Terven, Diana-Margarita Córdova-Esparza, Julio-Alejandro Romero-González +5

CICATA Qro., Instituto Politécnico Nacional, México · Facultad de Informática, Universidad Autónoma de Querétaro, México · CIDETEC, Instituto Politécnico Nacional, México +3

Long-Context Retrieval Evidence Retrieval RAG Evaluation Document QA Evidence-Grounded QA Hybrid Retrieval

Ask PDF

Sep 29, 2026

Follow the Entities: A Corpus Map for Agentic Search

Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval recorded in one, its requirements in another, and its latest status in a third. Recent LLM agents approach this by iteratively searching the full corpus rather than reading only a fixed set of top-ranked documents. However, when the corpus is exposed only as a flat collection of files, a relevant document gives no indication of how it relates to others, so the agent must rediscover these relationships for every query, often missing complementary evidence while simultaneously consuming substantial additional tokens. To address this, we introduce CorpusMap, a navigation layer that organizes the corpus around its recurring entities, which are identifiable from the documents themselves and can link a single document to many others across sources. Specifically, CorpusMap represents each recurring entity as an Entity Page that aggregates information about it and links to every document that refers to it, forming a graph between entities and documents that the agent can traverse to gather otherwise disconnected evidence. Moreover, since CorpusMap is constructed offline by resolving mentions of the same entity across documents, its links are shared across queries rather than rediscovered repeatedly at inference time. Using 7 different models with 3 benchmark datasets, we show that CorpusMap improves both evidence discovery and answer quality over raw-corpus agentic search while using fewer tokens on average, and further outperforms 4 alternative navigation layers, suggesting that entities serve as effective anchors for navigating large document collections.

Soyeong Jeong, Sujay Kumar Jauhar, Sung Ju Hwang +1

KAIST · Microsoft

Multi-Hop QA Agentic Search Graph-Based Retrieval Information Retrieval Multi-Document QA

Ask PDF

Abstract

In-Context Retrieval

Explore similar work

DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding

Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAG

Follow the Entities: A Corpus Map for Agentic Search