Knowledge-Intensive QA

Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literature). As humans interact with these corpora, they naturally accumulate experiential knowledge about artifacts, enabling them to quickly identify the complete set of relevant artifacts for each new task. However, existing AI agents lack appropriate memory solutions to build or reuse such artifact-grounded experience, leading to lower answer quality and higher online cost. Existing memory solutions extract and reuse information from prior task-solving traces, but they primarily focus on user preferences, factual attributes, or abstract reasoning patterns rather than persistent artifact-specific knowledge. We introduce ExperienceIndex, a novel experience layer for AI agents that captures and reuses knowledge about artifacts based on prior reasoning traces. ExperienceIndex stores two complementary forms of experience: (i) single-artifact experiences that summarize an artifact's contribution to prior tasks and (ii) artifact-pair experiences that encode structural relationships discovered during past reasoning. Integrated as lightweight middleware, ExperienceIndex uses an experience retrieval mechanism to guide agents toward the complete set of relevant artifacts for new tasks, improving both answer quality and efficiency. Across diverse corpora and agentic solutions with different search frameworks, ExperienceIndex delivers consistent gains, raising answer quality by up to 11.0 points and reducing online dollar cost by up to 50.5%. We further demonstrate two benefits: (i) cross-task generalization, where experiences accumulated from text-to-SQL tasks transfer to factoid QA tasks over the same artifact corpus, and (ii) teacher-student learning, where experiences from a stronger model enable a weaker model to reach comparable performance.

We consider the decision of whether to return an existing draft answer or revise it using retrieved evidence, as in answer-revision systems. Draft confidence estimates whether the current answer is correct, but the decision requires estimating the effect of a specified revision. For offline training and evaluation, we grade both the returned draft and its candidate revision under the same correctness judge, which makes repair, harm, and the gap to an oracle observable. We call this paired effect its recoverability, and we train policies to predict it before revision. On 25,870 held-out open-domain questions across three revision setups, a scorer trained on the paired outcome has greater area under the accuracy--revision-rate curve than a matched draft-correctness scorer in all nine Llama setup--seed fits, and gains 0.23--0.68 accuracy points on average at development-selected thresholds, a difference significant across training runs only for dense retrieval. The resulting policy improves on always revising and on average closes more than a third of the oracle gap, although it still applies 38--46% of the harmful revisions. When a draft-free standard-RAG answer is also available, however, choosing between the draft and that answer is stronger by about two points for Llama and four for OLMo, and adding candidate revision as a third option yields no significant gain. Recoverability describes one revision; its value as an available action also depends on the alternatives.

In the Era by Eon benchmark, each question states the rules for its answer, and code computes the answer from a generated company's data. When agents can run code, the four strongest models each answer 22 to 25 of 27 such questions, so the benchmark barely separates them. We add eight question templates that depend on hidden facts. No question or document states a hidden fact, and the records that seem to hold it show something else. Other data implies it. For example, the sales system says a customer dropped a purchase because of timing. On a recorded call, the customer blames an outage. For each generated company, code fills each template and computes an exact answer without a language model. We evaluate 12 agents. Each pairs a model with an agent program, which connects it to the company's systems. The best agent answers 18 of its 24 attempts, three per question, correctly. Four of the six models answer at most 6 of 24 with any program. The hardest questions require picking one of several similar records, such as which of three renewal offers a customer signed. All agents together answered two such questions correctly in only 1 of 84 attempts.

Probabilistic question-answering systems -- whether large language models (LLMs) themselves, retrieval-augmented generation (RAG), or trained multi-hop retrievers -- conflate "what is known" and "how to reason" into a single probabilistic computation: hallucination cannot be eradicated, evidence chains cannot be audited, and the system answers even when it does not know. We present LatWeave, which organizes knowledge into a multidimensional knowledge lattice and compiles multi-hop QA into three deterministic operators -- meet (constraint intersection), compare (lattice-order comparison), and abstain (structural abstention); LLMs appear only on the construction side (one-shot extraction) and the query-planning side, while the answer-generation path is zero-LLM, zero-task-training, and auditable end to end -- so that question answering over Web-published knowledge becomes reproducible item by item. Rather than claiming across-the-board SOTA, we characterize the operating envelope of this paradigm on six public benchmarks: when knowledge is complete (MetaQA, 39,093 questions) meet chains are near-lossless over three hops (any-hit 0.9975, on par with fully supervised KBQA); on templated multi-hop home ground (2WikiMultihopQA held-out n=1,258) EM 0.865, well above published structure-augmented RAG reproductions; on open-text deep composition (MuSiQue) and extraction-coverage gaps (HotpotQA) we report degradation honestly and attribute it to causes outside the lattice-algebra layer; and when information is incomplete (IIRC) we achieve structural abstention with abstain accuracy 0.971 and leak rate 0.029. Within the operating envelope, deterministic execution pays no performance penalty, and every step on the answer path can be recomputed -- precisely the source of end-to-end auditability.

Large language models are increasingly deployed as course-specific tutors, but their usefulness depends on grounding in vetted instructional materials that are often revised mid-semester. Our prior work built a multimodal retrieval-augmented generation (RAG) system over an authentic machine learning course corpus (Foundations of Machine Learning) and found that retrieval improved contextual grounding, but that fixed retrieval strategies were suboptimal. That motivates a different question: whether how a corpus is structured at ingest time matters more than how much is retrieved at query time. We present a controlled head-to-head comparison of two knowledge representations over an identical classroom corpus: (A) vector RAG, replicating the best-performing configuration from our prior study, and (B) an LLM-compiled wiki (Karpathy framework), in which the corpus is synthesized at ingest into linked concept pages with explicit cross-references and citations back to source materials. We evaluate 59 questions spanning single-fact recall, cross-unit concept linking, synthesis and explanation, and currency after a syllabus revision, scored by an LLM judge against a human-authored rubric. Both representations answered single-fact questions about equally well (9.33 vs. 9.96 of 10), but diverged sharply on questions requiring links across course units. The compiled wiki remained accurate and grounded (9.93; 100% grounded in cited sources), while retrieval scored lower and was markedly less grounded (8.14; 64%). The wiki's citations let students and instructors trace any claim back to the lecture that introduced it, adding a layer of dynamic retrieval that machine learning courses require. While further testing is needed, instructors using AI to support learning in ML courses should consider wiki-based structure for its potential to support foundational elements of best practice.

Two transformative classes of AI systems are reshaping how organizations operate: \textit{digital AI}, which reasons over enterprise knowledge to power chatbots and agent workflows; and \textit{physical AI}, which learns to control robots and autonomous systems from video, gameplay, and sensor telemetry. Both face the same foundational bottleneck: raw knowledge at scale, spanning heterogeneous modalities, locked in private corpora that existing AI infrastructure cannot access reliably or efficiently. We propose \textit{Universal Knowledge Perception (UniK)} as a common platform for both classes, covering the full knowledge lifecycle (ingestion, enrichment, indexing, retrieval, and continuous evaluation) across modalities from rich text and video to molecular data and sensor telemetry. We present UniK, built on Polymath Retrieval (multi-index fusion over automatically enriched indices) with no task-specific fine-tuning. Across five digital AI domains (medical literature, open-domain QA, chemistry, legal video proceedings, and government open data) UniK combined with an open-source 70-billion-parameter model consistently matches or outperforms frontier proprietary LLMs that are orders of magnitude larger: 76% RAG accuracy on government data versus 47% for GPT-5; 77.9% on medical QA without fine-tuning; topping all open-source chemistry pipelines. We show that the same infrastructure directly addresses the data curation, indexing, and retrieval challenges facing physical AI world model training, where the knowledge problem is harder but structurally identical.

Retrieval-augmented generation (RAG) can improve knowledge-intensive question answering, but the first design choice is easy to overlook: how should the source corpus be partitioned into retrievable units? Fixed-size chunks often return long passages whose relation to the question is only implicit. We introduce EAR, an Entity-Aware Partitioning approach for multiple-choice question answering (MCQA). EAR extracts normalized surface anchors from the question, answer options, and corpus; retrieves local windows around matching corpus anchors; and can attach a larger parent passage through an extractive summary. We evaluate EAR on a cleaned Massive Multitask Language Understanding (MMLU)-style subset of 153 questions selected by an automatic corpus-support heuristic and using decontaminated public textbook text. Across same-protocol top-k = 3 and top-k = 8 sweeps with Mistral, Gemma, and DeepSeek, EAR entity-window reduces retrieved words by 37.5-40.2% relative to chunks. Observed accuracy changes are +5.2, +1.3, and -3.9 points at top-k = 3, and +5.9, -3.3, and -4.6 points at top-k = 8; none of the entity-window differences is statistically significant. The scoped contribution is methodological: EAR provides a compact and inspectable retrieval unit, while its rule-based anchor extractor remains domain-specific and requires separate validation before transfer.

We present ORQA, a method for testing occupation-level knowledge in large language models. Prior methods either map abstract LLM skills to occupations via task definitions or utilize expert knowledge which is difficult to obtain at scale and expensive. ORQA complements both of these methods by connecting O*NET occupations to trusted occupation-specific websites (such as regulatory agencies, licensing bodies, professional organizations, and government publications) and converting these into source-traceable question-answer pairs. A combination of an automated pipeline and human review produces a set of high quality questions about occupations. The question set created via our method covers 116 occupations from all 21 major groups in the SOC, with 480 questions sourced from 187 different websites. Each question is designed to probe a real-world skill question that is relevant to the occupation in question. We test 15 state-of-the-art frontier and open-weight models via this method. Claude Opus 4.6, GPT-5.4 and Claude Sonnet 4.6 all perform the best at approximately 58-62% while smaller open-weight models achieve approximately 33-41% performance. Performance varies significantly across occupations. Healthcare-related occupations achieve the highest performance (78%) while Office and Administrative Support achieve approximately 40%. Performance on individual occupations (e.g. Sheet Metal Workers and Fish and Game Wardens) is essentially zero. We also find that open-ended questions and weighting by wage bill do not significantly affect the ranking of models on this benchmark. We believe that leveraging existing trusted occupation-specific information to test LLM knowledge in professional domains may be a scalable and useful method for evaluating occupation-level AI performance in the future. Results and data are available at orqabench.org.

Software repositories contain vast amounts of data on code contributions, bug reports, and project activities, yet this information remains challenging for non-technical stakeholders and developers to access due to limited expertise in querying repositories. To address this, we introduce a novel chatbot architecture leveraging OpenAI's GPT-4 model for automated extraction and analysis of repository data. In contrast, our architecture takes a structured path first by parsing the user's query to extract relevant parameters, then selecting the correct tool to employ based on that analysis, and finally invoking the GPT-4 model to create a highly detailed response. In contrast to previous work based on multi-component systems with embedding models and document retrievers, our architecture inverts the process by relying on prompt engineering and tool selection to fit with the query intent. To validate our approach, we conducted experiments on various question types, including Issues, Pull Requests, Commits, Compound Questions, and General Repository Information, evaluating our target prompts' ability to improve the accuracy of responses from the model. Beyond demonstrating the utility of this architecture to a diverse set of users, our findings suggest that this architecture can make repository data more accessible to technical and non-technical audiences through the production of actionable insights.

Giving an agent a file about a named expert can supply hard-to-find material, produce a recognizable persona, or change what the agent decides. These are different claims. We test each one. mimeo is an open-source tool that finds a person's public work, checks each extracted quotation against the cached source text, and writes a file an agent can load. Eight logged builds averaged 38 model calls; the check rejects 13.2% of extracted quotations. We tested four expert files with one coding-agent harness. Knowledge access was clearest: mimeo answered all 20 obscure, quotation-heavy questions; no closed-book condition answered more than 10. Keyword search (BM25) over the same pages answered 15-17, a gap this sample cannot resolve. Grounding showed one clear benefit: personas written from model memory misstated a documented position on 1-4 of 20 answers under every grader; the plain agent and mimeo never did. Every persona was easy to spot on short open prompts, and adding task material lowered identification by 18-23 points. mimeo was no more identifiable than a from-memory profile. Judgment transfer remained unresolved because both tests hit their ceiling: every condition found 94-97% of the problems planted in engineering tasks and scored 94-100% on 16 new application scenarios. An AI-judged "sounds like the expert" score changed with the judge: two of four preferred answers based on a model's stereotype, while two found no difference on the same text. That is a caution against relying on a single AI judge. The evidence supports mimeo as a compact, inspectable reference on a person, not as a demonstrated transfer of their judgment. Toolkit and expert profiles: https://github.com/K-Dense-AI/mimeo

Knowledge-base question answering (KBQA) systems rely on effective retrieval and reasoning mechanisms to generate accurate answers from external knowledge sources. However, developing reliable KBQA systems for low-resource languages such as Bangla remains challenging due to limited retrieval-focused research, scarce language resources, and difficulties in grounding generated responses in external knowledge. In this work, we propose HybridRAG-BN, a retrieval-augmented framework for Bangla KBQA that integrates hybrid retrieval using BM25 and BGE-M3, answer generation using the GGUF version of Gemma-4-31B-Instruct, and a LoRA-fine-tuned Gemma-4-31B-Instruct model for answer verification and refinement. To further improve robustness, the framework incorporates a post-processing stage that addresses unresolved cases through fallback answer replacement and DuckDuckGo-assisted retrieval. Experimental results demonstrate the effectiveness of the proposed framework, achieving token-level F1 scores of 0.71654 and 0.72912 on the public and private leaderboards, respectively, securing first place in the competition.

Enterprise agents often need to integrate heterogeneous knowledge sources: documents for narrative facts, tables for computation, and dependency graphs for file relationships. Existing benchmarks typically evaluate retrieval or tool use without distinguishing whether an agent first selects the appropriate knowledge sources. We introduce WorkSurface-Bench, a benchmark for evaluating this capability as surface routing. It contains 1,151 atomic tasks derived from persona-scoped Workspace-Bench-Lite workspaces, spanning document, table, graph, and cross-surface questions. Its reference answers are auditable: table answers are reproduced through executed DuckDB queries, document answers are grounded in verified text spans, and graph answers are traced to source dependency annotations. We evaluate four model backbones across six controlled agent settings, yielding 27,624 protocol-error-free trajectories. Under gold-constrained tool access, agents achieve 98.7-99.8 Route F1, while Answer remains only 56.1-75.3 percent, showing that correct surface selection is necessary but insufficient for task completion. Matched interventions further show that surface hints improve Answer for three of four models, whereas removing irrelevant tools primarily improves routing and efficiency. In an independent three-annotator audit, all 200 sampled tasks pass all six quality criteria by majority vote, with 192 receiving unanimous judgments on every criterion. We release the dataset, construction pipeline, scoring code, and agent harness at https://github.com/haolpku/WorkSurface-Bench.

Recent advances in RAG aim to optimize for performance by paying high ingestion costs for knowledge ingestion: building knowledge graphs or extracting SQL tables. In this work we show that the operations that such knowledge bases allow can be replicated with zero ingestion costs (not even a vector database); in fact our solution, Zero-Ingestion ScalableRAG, handily out-performs all baselines (including knowledge graph approaches) in three out of the six corpora considered here, and only marginally missing maximum performance on the other three, with average accuracy across all six datasets 7.36% above the next most competitive baseline. It achieves this by keeping a workspace of document sets and values sets that it can write into and read from, allowing for on-the-fly aggregative reasoning in all situations where grouping is required on a primary key that is in one to one correspondence with a subset of the total document set. Capping the number of LLM calls by a constant independent of the corpus size, we also introduce Limited-Ingestion ScalableRAG, which does use a minimal vector database as well as an automated pattern discovery from a sample of documents, to further improve accuracy at scale. Our code is available at https://github.com/cohesity/ScalableRAG .

Real-world document tasks often ask professionals to answer questions from annual reports, regulations, clinical guidelines, and technical manuals that span hundreds or thousands of pages. Some questions also require comparing related reports. Reliable long-document understanding is therefore a prerequisite for using LLMs in compliance, clinical, financial, and engineering workflows, where decisions must be traceable to specific evidence pages and the cost of an unsupported answer is high -- yet most existing benchmarks still measure short-context or single-page QA. We introduce XL-DocBench, a fully human-verified benchmark for extra-long document understanding, with 1,519 retained questions from six professional domains and contexts up to 2,303 pages. XL-DocBench goes beyond page-level lookup. 1,103 examples (72.6%) use multiple evidence pages. The final set also includes 556 questions (36.6%) that use tables, charts, or figures, and 165 questions (10.9%) that require evidence from multiple documents. Each question has one of twelve reasoning labels, expert-annotated evidence pages, a typed verification rule, and an answer format, including 218 None-answer cases. We build the benchmark with a tree-guided synthesis pipeline followed by artifact filters and full verification by 194 human experts. By coupling extra-long professional contexts with page-level evidence and typed rules, XL-DocBench fills a gap left by prior single-page, short multi-page, or text-only long-context benchmarks, and lets future work attribute system failures to retrieval, evidence use, or rule following rather than to a single leaderboard score. The results show that current systems still struggle with long contexts, multi-page evidence, and structured reasoning over professional documents.

Large language models are increasingly used to assist scientific reading, but existing evaluation methods often fail to detect whether answers are supported by verifiable citations. We introduce ResearchQA, a benchmark of 6,211 single-paper question-answer pairs from 494 open-access papers spanning eight domains and four question types: lookup, comprehension, multi-hop, and adversarial. ResearchQA is designed for citation-grounded evaluation: it permits multiple valid supporting passages for a claim and rewards grounded refusal when the source paper does not support an answer. We evaluate eight leading closed- and open-weight models in a citation-grounded chat-with-paper setting using a deterministic citation matcher and an LLM-based rubric evaluator. Citation-based metrics separate systems more clearly than LLM-evaluator scores: section coverage and citation accuracy vary substantially across models, while evaluator scores remain tightly compressed. We further find that open-weight models approach the best closed-model citation accuracy while achieving 3 to 6 times lower per-example latency. We release the benchmark, evaluation harness, and evaluator prompt.

LLM agents now often answer questions from knowledge bases they help maintain. A common intuition says progressive disclosure should make this cheaper. Instead of loading one large index, the agent reads a compact catalog and one-line page summaries, then opens only the pages it needs. We tested that intuition in a preregistered study on a real 709-page markdown knowledge base maintained by an LLM. We retrofitted it for progressive disclosure and built four versions that differ only in how the agent reaches the pages. The pages themselves are identical in every version, so any difference comes from the access structure alone. Each version was tested three ways, with the agent following a set protocol, choosing its own path, or made to load the catalog first. A judge from a different model family graded the answers blind against verified reference answers. A preparatory pilot changed the question. A capable agent never loaded the large index at all. It worked out from the question where a page was and read it directly. The saving we set out to measure did not exist for such an agent, so we made answer quality the primary outcome. Quality held. Answers from the retrofitted knowledge base were as good as answers from the original, within a margin we set in advance. Two limits apply. Our human rater and the model judge agreed far less than the plan required, so the quality result rests on the judge, backed by sensitivity checks. Quality was also not shown to hold when the agent was forced to load the catalog first, or on the two most reliably graded criteria under a stricter test. Cost fell clearly in every condition we tested, and the retrofitted version cited fewer pages and took fewer tool turns per answer.

We present KrishokChat, the first citation-grounded Bengali agricultural instruction-tuning dataset for crop advisory in low-resource settings. We establish a foundation of 290 hierarchical Knowledge Nodes, extracting disease symptoms, management practices, chemical dosages, and verbatim citations from 129 domain-filtered agricultural manuals. Every training instance inherits a verified citation header, guaranteeing 100% citation provenance. Using a Partitioned Seed Generation Matrix, these nodes are expanded into 139,200 supervised fine-tuning pairs, and augmented with 5,300 chemical safety and 1,000 adversarial safety instances, yielding 145,500 QA pairs across 18 crop categories. To evaluate real-world performance, we introduce the Farmer Benchmark, comprising 1,001 authentic farmer queries curated from field surveys and digital portals. Empirical evaluation on Gemma-4-E2B reveals that while fine-tuning on KrishokChat vastly improves structured formatting, standalone models still struggle with exact chemical dosage generalization. This highlights the dataset's true value as a verified knowledge base for retrieval-augmented generation (RAG) rather than mere parametric memorization. All data, code, and benchmarks are released under CC-BY-4.0.

LLM agents in knowledge intensive question answering take retrieval and reasoning actions with incomplete knowledge about whether their current answer is uncertain, unsupported, or already complete. This produces two failure modes: committing to confident but unsupported answers, which hurts accuracy, and over-retrieving when the evidence in hand already suffices, resulting in wasted compute. To give agents a more complete picture of the state space they are operating in, we introduce calibrated verifier telemetry (CalVerT), which augments the agent's state with additional telemetry: a calibrated self-confidence score and a grounding verifier score. We show that CalVerT can improve agents in both training-free and training-based settings. On four QA benchmarks, we find that CalVerT raises F1 by triggering retrieval in cases where agents over-rely on parametric knowledge, while cutting redundant retrieval in cases where agents have sufficient context to answer. We show that CalVerT can augment existing QA frameworks without training. Moreover, CalVerT also improves trained systems: by simply augmenting an agent's state with telemetry, we observe improvements after reinforcement learning, as compared to an agent with identical training but no CalVerT telemetry.

Agentic search over large corpora relies on retriever-mediated interfaces (e.g., BM25 or ColBERT) for scalable candidate discovery. While effective at ranking relevant documents, these interfaces expose evidence only as ranked results or bounded document views, limiting agents' ability to reorganize material and verify constraints across documents. Direct Corpus Interaction (DCI) addresses this limitation by exposing shell-executable corpus operations for flexible search, filtering, comparison, and verification. However, full-corpus terminal commands become slow and unstable as the corpus grows, degrading performance and efficiency. We introduce DR-DCI, a retriever-steered DCI framework that treats retrieval as an agent-callable action for expanding a local workspace. Rather than operating directly over the full corpus, the agent dynamically pulls relevant documents into an evolving workspace and conducts DCI operations within it. This design combines retriever-level recall with DCI-style precision: retrieval keeps exploration scalable, while DCI preserves the local operations needed for effective evidence resolution. Experiments show that DR-DCI is both effective and efficient across scales. On Browsecomp-Plus, DR-DCI reaches 71.2% accuracy, improving over raw DCI and ablated variants by up to 8.3 points while reducing tool usage, wall time, and estimated cost. With workspace-preserving context reset, accuracy further improves to 73.3%. In corpus-scaling experiments, DR-DCI remains effective from 100K to 10M documents, whereas raw DCI becomes unstable and BM25 performs substantially worse. DR-DCI also scales to a 20M-scale file-per-document Wiki-18 QA setting, achieving an average score of 63.0 across six benchmarks and outperforming retrieval-based and trained search-agent baselines. Ablation analysis further shows that ranked previews and inter-document DCI are key to performance.

TimeLens is an AI-powered bilingual mobile guide for the Grand Egyptian Museum (GEM). Pointing a phone at an exhibit, a visitor sees the artifact recognized in real time and can ask follow-up questions answered in English or Arabic. The work addresses three problems specific to in-gallery deployment: fine-grained visual similarity among 51 catalogued artifacts (many near-identical Ramesside statues), the gap between curated training data and handheld camera conditions, and the risk of an AI guide stating unsupported historical facts. Two engineering contributions are reported. First, an on-device artifact detector was developed through a data-quality-driven iteration study -- from foundation-model auto-annotation (YOLO-World), through spatial label-cleaning rules, to a fully hand-annotated dataset -- isolating label quality as the decisive factor: the final YOLOv8n model resolves every previously failing class while remaining a 5.97 MB TensorFlow Lite asset that runs in real time on a mid-range phone ([email protected] = 0.995, [email protected]:0.95 = 0.924). Second, a bilingual Retrieval-Augmented Generation (RAG) guide, grounded in a 108-record ChromaDB knowledge base, was benchmarked across seven candidate language models, with Gemma 4 E2B (Q4 K M) selected; ten targeted optimizations reduce end-to-end latency from over 30 s to approximately 10 s. Both subsystems are integrated in a production Flutter application with bilingual interface, museum location gating, and text-to-speech support.

Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved. In contrast, real-world questions are often not paired with accurate evidence documents. The useful evidence resides in massive data lakes, making search a prerequisite for answering. However, there is a lack of comprehensive benchmarks that require both searching and reasoning over large data lakes. To this end, we introduce LakeQA, a comprehensive benchmark for search-centric question answering over data lakes that jointly emphasizes searching and reasoning capabilities. LakeQA is built on a heterogeneous collection of approximately 9.5 TB of text resources from Wikipedia and open-source government data, spanning structured and unstructured data. To ensure task quality, each sample is annotated by at least one Ph.D.-level expert. Each task requires long-horizon multi-hop reasoning with implicit intermediate steps: agents need to discover the correct documents and then compose evidence across sources to produce the answer. Experimental results on seven frontier LLMs demonstrate that LakeQA is challenging. For instance, GPT-5.2 achieves only an exact-match score of 18.37% on LakeQA. Overall, LakeQA provides a realistic testbed for developing LLM agents that can both find and analyze data in modern data lakes.

We introduce Office Comprehension Bench (OCB), the first public benchmark to jointly evaluate LLM systems on Word, Excel, and PowerPoint comprehension over native file formats (.docx, .xlsx, .pptx) and their variants. OCB consists of two tracks. File Fidelity Q&A tests structural and visual perception of office artifacts - tables, charts, embedded images, formulas, and app-specific elements such as headers, speaker notes, and named ranges. Domain Q&A tests expert-level reasoning grounded in real-world industry documents across 12 professional domains, with queries requiring multi-step analysis and synthesis across documents. Each reference answer is decomposed into atomic, binary-gradable claims, and an ensemble of LLM judges scores responses against each claim independently. Even the strongest frontier system in its default reasoning mode reaches only about 59.3% on Domain Q&A; increasing thinking depth within a tier does not move performance materially, while moving to a higher product tier yields modest gains. We release the dataset, evaluation tooling, judge prompt, and a public leaderboard.

Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supervision and cannot distinguish correct from incorrect statements within a reasoning trace. Sentence-level alternatives offer finer-grained feedback, but typically rely on NLI verifiers, LLM judges, or knowledge-verification pipelines that are expensive to deploy at RL scale and often unreliable for rare-entity facts, where accurate reward signals are especially important. We propose CorVer (Corpus Verify), a lightweight, plug-in-ready process reward that replaces neural verifiers with a corpus-grounded signal derived from Wikipedia co-occurrence statistics. CorVer assigns sentence-level credit and maps it to token-level advantages via a simple alignment, requiring only a 0.5B extractor and a single corpus lookup per sentence. Across 30 (model, benchmark) cells spanning six instruction-tuned models (3B to 14B) and five QA benchmarks, CorVer improves over the raw baseline for every cell, with an average TriviaQA gain of +4.1 pp. It also outperforms four neural-verifier baselines in 18 of 20 cells under their feasible configurations, while training 4.8 to 8.4x faster.

Large Language Model (LLM) search agents have shown strong promise on knowledge-intensive tasks through iterative reasoning and retrieval. Most existing systems rely on retrievers that return ranked documents from a pre-built index. We explore a complementary paradigm in which the agent treats the corpus as the search environment and finds evidence through executable shell commands. We introduce GrepSeek, an optimized direct corpus interaction (DCI) agent that learns to find, filter, and compose evidence over large text corpora. To stabilize reinforcement learning (RL) over large corpora, we train in two stages: first, we initialize the policy using verified, causally grounded search trajectories generated by an answer-aware Tutor and an answer-blind Planner; then, we refine the policy using Group Relative Policy Optimization (GRPO). To make DCI practical at scale, we introduce two semantics-preserving execution optimizations: Pruned Adaptive Command Execution, which reduces shell-based search latency by up to $77\times$ on a 14GB corpus with 21 million documents using a compact auxiliary structure, and Sharded-Parallel Corpus Search, which achieves up to $7.6\times$ speedup without additional preprocessing; both preserve equivalence with sequential execution. Across eight open-domain QA benchmarks, GrepSeek achieves the strongest overall performance, with a statistically significant relative improvement of $5.7\%$ over the best baseline. Our analysis shows how DCI-optimized agents conduct flexible and effective compositional search through direct corpus interaction.

Reliable question answering requires identifying not only whether an answer is correct, but also which available knowledge the prediction depends on. In realistic LLM-based QA, this knowledge may come from context, retrieval, decomposition, or intermediate reasoning, forming a noisy and redundant candidate space rather than a clean gold evidence set. We study \emph{knowledge dependency estimation}: estimating the sensitivity of a fixed black-box QA model to different candidate knowledge units. The challenge is to obtain fine-grained dependency scores without exhaustive test-time perturbation while modeling redundancy, substitutability, and complementarity. We propose \textbf{Knot}, a structured rank-aware knowledge dependency estimator. Knot learns from subset-level counterfactual supervision, models subset sensitivity through coverage over latent dependency factors, and derives rank-aware unit scores to identify influential candidates. Across multiple-choice and generative QA benchmarks, Knot outperforms all compared baselines in subset-sensitivity prediction and produces more faithful unit rankings than deployable baselines without extra QA-model calls; when used for practical risk screening, its dependency scores help flag error-prone QA predictions early.

Recently, there has been increased interest in Small Language Models (SLMs), which are fast, show good performance, and have lower hardware demands than large language models (LLMs). However, SLMs hallucinate more frequently than LLMs, impacting their ability to solve complex multi-step reasoning problems as early mistakes cascade to the final response. To address this, existing works think-first followed by iterative retrieval to reduce hallucination. We argue that the think-first strategy is not always necessary as we find that: (i) SLMs are often accurately confident in their initial answer and, (ii) hallucinations can actually be beneficial for honing in on the true answer. As such, we position our work as an inversion of this strategy, i.e., answer first-reason later. We propose a cognitively-inspired framework where the model is first allowed to quickly answer the question (System-I (zero-shot)) and then resorts to deeper thinking (System-II) based on evidence retrieved from a knowledge source using the initial hypothesis. By combining System-I and System-II style thinking, we show that our method can outperform prior work that takes the traditional think-first route on various multi-step question-answering benchmarks.

Evidence construction--the stage that determines which passages reach the language model before generation begins--is evaluated paradigm by paradigm, leaving practitioners with no principled way to diagnose which organization strategy fails, where, or why. We introduce AuthTrace, a diagnostic benchmark built on thematically dense single-author corpora where near-miss distractors share style, topic, and vocabulary with the required evidence. AuthTrace provides explicit quoted evidence, exact fan-in annotation, and a unified pack-level protocol measuring evidence recall, evidence precision, and answer correctness. A fan-in gradient--the number of source documents required to support the answer--serves as the primary diagnostic axis, enabling controlled comparison across retrieval, memory, graph, and structured-evidence paradigms. Evaluating eight systems across two QA models, we find that evidence recall is the strongest observed predictor of answer correctness under the primary reader-judge pair (r = 0.96); most failures stem from missing evidence rather than answer synthesis. Fan-in further exposes paradigm-specific collapse patterns: flat retrieval degrades 2-3x faster than thematically organized evidence construction. These results show fan-in decomposition to be a reusable diagnostic lens for identifying where evidence-construction systems fail and which paradigm best serves a given workload.

Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-world scenarios require external knowledge that is not directly observable in the image to answer correctly. We introduce WikiVQABench, a human-curated knowledge-grounded VQA benchmark constructed by systematically combining Wikipedia images, their associated article captions, and structured knowledge from Wikidata. Our pipeline uses large language models (LLMs) to generate candidate multiple-choice image-question-answer sets. All generated instances are subsequently reviewed and curated by human annotators to ensure factual correctness, visual-text consistency, and that each question requires external knowledge in addition to visual evidence for correct resolution. WikiVQABench comprises a substantial collection of Wikipedia images with curated multiple-choice questions designed to benchmark knowledge-aware vision-language models (VLMs). Evaluation of fifteen VLMs (256M-90B parameters) reveals a wide performance range (24.7%-75.6% accuracy), demonstrating that the benchmark effectively discriminates model capabilities on knowledge-intensive reasoning. The dataset and benchmarking code are publicly available.

Multimodal large language models are increasingly used as agent backbones that understand multimodal inputs, plan retrieval actions, invoke external tools, and reason over retrieved information. Yet existing benchmarks rarely evaluate this ability in short-video applications, where a paused frame is often visually ambiguous and answering requires vertical, long-tail, and fast-evolving domain knowledge. We introduce SVFSearch, the first open benchmark for short-video frame search in the Chinese gaming domain. SVFSearch contains 5,000 four-choice test examples and 4,198 auxiliary training examples, each centered on a paused game scene from a real short-video clip. To support fair and reproducible evaluation, SVFSearch provides a frozen offline retrieval environment with a game-domain text corpus, a topic-linked image gallery, and text, image, and multimodal retrieval interfaces, avoiding reliance on uncontrolled web search APIs. We evaluate representative paradigms ranging from direct QA and RAG workflow to Plan-Act-Replan agents and learned search models. Results reveal a large gap between model-only answering, practical agentic search, and oracle knowledge: the best open-source direct-QA model reaches 66.4%, the best practical agent achieves 79.1%, and oracle knowledge reaches 95.4%. Further analysis exposes bottlenecks in visual grounding, retrieval quality, evidence-grounded reasoning, and tool-use behavior, including over-search, answer-only shortcuts, and retrieval-induced misleading.

Despite substantial advances in large language models (LLMs), generating factually consistent responses for knowledge-intensive question answering remains challenging. These difficulties are primarily due to hallucinations and the limitations of LLMs in bridging long-tail knowledge gaps. To address this, we propose AMATA, an Adaptive Multi-Agent Trajectory Alignment framework that dynamically integrates external knowledge to improve response interpretability and factual grounding. Our architecture leverages six specialized agents that collaboratively perform structured actions for complex question reasoning. We formalize multi-agent collaboration with external tools as a trajectory preference alignment problem, incorporating question-aware agent customization and inter-agent preference harmonization. AMATA introduces two principal innovations: (1) Intra-Trajectory Preference Learning, which learns objective-oriented preferences to prioritize critical agents, and (2) Inter-Agent Dependency Learning, which captures cross-agent tool dependencies through a novel dependency-aware direct preference optimization technique. Empirical results show that AMATA consistently outperforms baseline approaches, knowledge-augmented frameworks, and LLM-based trajectory systems on five established knowledge-intensive QA benchmarks. Further analysis demonstrates the efficiency of our method in reducing token consumption.