LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
Transforming a large language model (LLM) into a vision-language model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as sim…
Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models
Multimodal large language models (MLLMs) often fail in fine-grained visual reasoning, as question-relevant visual cues are diluted by dense and redundant image tokens. Recent multimodal reasoning methods usually extend c…
Multimodal ReasoningVisual ReasoningMemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capability: long-context LVLMs and memory-augmented agents. However, no exis…
Information ExtractionVisual GroundingAnalyzing Speaker Strategy in Referential Communication
We analyze a corpus of referential communication through the lens of quantitative models of speaker reasoning. Different models place different emphases on linguistic reasoning and collaborative reasoning. This leads mod…
Bandits Warm-up Cold Recommender Systems
We address the cold start problem in recommendation systems assuming no contextual information is available neither about users, nor items. We consider the case in which we only have access to a set of ratings of items b…
Multi-Armed BanditsRecommendation Systems