Knowledge
-
Pistis Technical Report
2026-09-23 08:03:45Heyun Chen, Xiaohan Lan, Jiaxi Li, Zhilin Lu, Qi She, Weiwen Xu, Fei Yu, Yujie Zhong, Jinghuan Chen, Zijian Feng, Siyu Jiao, Yiheng Lin, Xinhao Wang, Sihan Yang, Jieyu You, Changbin Zhang, Hengyu Zhang, Xudong Zhang, Yunqing Zhao, Shuai ZhengAbstract
We introduce the Pistis model family, comprising 27B- and 9B-parameter multimodal large language models built on Qwen3.6 and Qwen3.5, respectively, and developed through a general and scalable post-training framework. The framework first establishes a strong foundation through large-scale multimodal supervised fine-tuning (SFT). Building on this SFT foundation, we propose Interleaved Distillation and Reinforcement Learning (IDRL), a novel post-training paradigm that tightly integrates on-policy distillation and reinforcement learning within a single training loop. By alternating between the two objectives, rather than optimizing either in isolation or combining them in a static joint loss, IDRL enables more effective knowledge transfer, greater optimization stability, and more precise credit assignment for long-horizon agentic trajectories, leading to stronger performance while mitigating common capability trade-offs. At both model scales, the framework produces two specialized variants: Pistis-Thinking, designed to strengthen deep multimodal reasoning, and Pistis-Agentic, which additionally incorporates agentic trajectory data to support long-horizon planning, iterative reasoning, and tool use. Pistis-Agentic is particularly strong in multimodal search. Both scales outperform their corresponding base models. Beyond model-parameter optimization, we further introduce Pistis-Auto-Harnessing (PAH), a system-level method that automatically improves the agent's inference harness through iterative optimization. Experiments demonstrate that PAH enhances the model performance without updating the model parameters or increasing the interaction budget.
Abstract (translated)
URL
https://arxiv.org/abs/2609.28554
PDF
-
WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents
2026-09-23 07:49:24Jingjie Ning, Xueqi Li, Yibo Kong, Dongting LiAbstract
AI research agents need reliable knowledge of how their experiments change outcomes. We introduce WhatWorkedBench to measure experimental understanding, the accuracy of predictions about component changes after budgeted experimentation. Agents inspect code, select measurements, and submit a response surface, a table predicting scores for every configuration of component settings. Exhaustive CPU execution supplies reference effects for changing each component while holding the others fixed. These effects capture combinations of changes across 36 tasks from 30 data sources and 8 workflow types, with 1248 configuration records. Core evaluation combines 4,206 numerical-control records across all eight families and 108 agent episodes across the original six. At eight new measurements, pair-effect ridge selects an optimum on 15 of 22 sources and limits every effect error to 10% of score range on three. Fitting a Gaussian process (GP) to the same agent observations raises effect recovery, accuracy relative to true effect magnitude, from 0.632 to 0.698 in the original Flash cohort and from 0.621 to 0.720 in an additional cohort. On six completed beat-detection and graph submissions, the same-observation GP raises family-macro recovery from 0.303 to 0.455. On six workflows with six binary options at 20 new measurements, encoding code equivalences, configurations with identical behavior, raises GP recovery from 0.248 to 0.462. WhatWorkedBench supports research on experimental agents, adaptive experimental design, numerical inference, and use of program structure.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27490
PDF
-
A Modular Dual-Arm Robotic Cell for Disassembly and Repair of Industrial Control Electronics
2026-09-23 07:29:14Maximilian Ruhe, Fabian Harlacher, Christian Friedrich, Martin KipfmuellerAbstract
Industrial control electronics such as programmable logic controllers, servo drives and operator panels are routinely repaired in plant maintenance, but were never designed for automated disassembly. This paper presents a modular dual-arm robotic cell for repair-oriented disassembly, using two collaborative manipulators, interchangeable tools, red-green-blue-depth (RGB-D) and wristlevel perception, force/torque sensing and a Robot Operating System (ROS) 2- based control with Behavior Tree (BT) execution, teleoperation, digital-twin support and bounded learning-based contact skills. The process is decomposed into sequence planning, symbolic execution with fallbacks, force-limited tool skills, visual condition assessment and demonstration-based adaptation. A CADderived device graph encodes the disassembly order, access constraints, tools, feasible removal directions and verification states and converts them into operation objects for the BT and motion layers. Grounded in three representative devices, the cell covers screw removal, damaged-fastener fallback, snap-fit opening, connector release, cooperative printed circuit board (PCB) extraction and condition-based repair decisions. The main contribution is an architecture linking sequence knowledge, perception, verification and force-aware skills through one ROS 2 interface across simulation, teleoperation and real hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27466
PDF
-
EvoAudio: Recursive Self-Improvement for Audio Understanding
2026-09-23 05:45:11Yuxiang Wang, Shengbo Cai, Yingda Shen, Ming-Hao Hsu, Qinke Ni, Liqiang Zhang, Teddy Sun, Steve Yevs, Zhizheng WuAbstract
Audio language models understand what is said far better than how it sounds. Closing this gap takes more than data. Detailed acoustic annotation is costly, labels from stronger models inherit their errors and limits, and fixed data cannot adapt as the learner improves. We therefore propose EvoAudio, a recursive self-improvement system for audio understanding. To our knowledge, it is the first to evolve the model, waveforms, questions, and difficulty in one closed loop. EvoAudio uses the current model's performance to set the focus and difficulty of the next training data. A library of audio tools then constructs questions whose answers follow from how the audio was made, providing verifiable supervision without new human annotation. Reinforcement learning updates the model, and validation decides whether it enters the next evolution round. Across 13 rounds, EvoAudio improves five models with different audio encoders and language backbones on MMSU, MMAU-Pro, and MMAR. It achieves the highest average for every backbone, raising overall performance by up to 6.3 points. The improvement unfolds over successive rounds, with each stronger model starting the next round.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27389
PDF
-
Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction
2026-09-23 04:55:09Jialu Wang, Jianing Deng, Shuqing Luo, Yuanzhe Li, Dongwei Wang, Jingtong Hu, Huanrui Yang, Song Wang, Tianlong ChenAbstract
Unlearning ensures LLM compliance by removing the influence of private or copyrighted training data. However, since LLM models typically undergo post-training compression, like quantization, in practical deployment, it has been observed that the unlearning effect can be substantially weakened, with the forgetting behavior degrading more severely than that of model utility. This paper proposes a quantization-robust unlearning framework that makes forgetting robust to quantization while maintaining overall model utility. We analyze this gap through the lens of loss landscape. Specifically, our analysis reveals a curvature-based criteria that pinpoints sensitive weights in the unlearned model that leads to both non-robust forgetting and reduced utility. We therefore propose sensitivity-guided noisy regularization, which is applied on the sensitive parameters to steer the model convergence towards a smoother minima of uniformly low forget and retain losses. Balancing unlearning and utility, we further propose forget-critical optimization, which updates only forget-critical layers, preserving most of the network to retain useful knowledge. Extensive experiments on the MUSE and TOFU benchmarks across multiple LLM unlearning algorithms show that our approach achieves substantially more quantization-resilient forgetting while maintaining utility.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27355
PDF
-
Constraint-Driven Context Engineering: Designing Domain Interfaces for AI Systems
2026-09-23 04:53:47Xiwei Xu, Chen Wang, Mengmeng Yang, Yipeng Zhang, Jacky Jiang, Suyu Ma, Youyang Qu, Ming Ding, Liming ZhuAbstract
Generative AI systems are increasingly deployed to address domain problems. These systems operate under technical, regulatory, institutional, and normative constraints that define acceptable AI behaviour and outcomes within their domains. We observe a recurring pattern in our industry engagement: partners often arrive with a functioning but relatively generic AI solution. The challenge is no longer to build an AI system from scratch, but to improve the quality and domain appropriateness of an AI-generated solution. In these settings, the limiting factor is often the quality, scope, and structure of the context available to the system. Yet, existing context engineering approaches primarily focus on supplying domain knowledge through retrieval, memory, and tools, with limited support for systematically identifying and operationalising the constraints that govern AI systems in their operational environments. This paper proposes Constraint-Driven Context Engineering (CDCE), a design approach for engineering domain interfaces for AI systems. Drawing on software architecture design and Domain-Driven Design (DDD), CDCE treats domain constraints as first-class design drivers. It identifies and characterises constraints, determines the required context assets, and designs representations through which these assets are made available to AI systems. We conducted a comparative multiple-case study with industry and public-sector partners across educational assessment, healthcare decision support, and financial-distress prediction. Depending on their characteristics, constraints can guide AI behaviour, enforce permissible boundaries, or support verification of AI-generated outcomes. The cases demonstrate CDCE's applicability across contrasting domains and show how constraint characteristics shape the resulting domain interfaces.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27354
PDF
-
Large Knowledge Model: From Papers to a Scientific Reasoning Landscape
2026-09-23 03:32:50Yuan Huang, Sihan Hu, Hongyu Gu, Chao Ma, Jiaxing Zhang, Zhiyong Zou, Caiyu Fan, Yan Xiao, Mingjun Xu, Chenyu Xie, Mingzhen Ju, Zhehao Ma, Qi Zhang, Baozong Wang, Yu Li, Zhiyuan Yao, Ruoxue Liao, Xinyu Li, Linfeng Zhang, Kun Chen, Weinan EAbstract
Accumulated scientific knowledge advances inquiry when prior findings help researchers choose new questions, design investigations, and interpret results. Realizing this value at scale requires access to the reasoning that connects research problems, scientific procedures, conclusions, and evidence. We introduce the Large Knowledge Model (LKM), a scientific knowledge infrastructure that transforms the literature into a shared, computationally accessible reasoning resource. LKM represents papers as source-grounded reasoning graphs, couples structural traversal with semantic retrieval over the same objects, and aligns related questions, claims, and reasoning chains across papers. This representation forms a Scientific Reasoning Landscape with three connected views: a Question Landscape that organizes research problems and open directions, a Workflow Landscape that exposes reusable scientific procedures, and an Evidence Landscape that connects conclusions to their support, disagreement, and conditions. The unified substrate supports reasoning-aware scientific search, evidence-grounded question answering, comparative evidence analysis, and research planning. Researchers and agents can retrieve relevant work through its scientific intent, synthesize answers with inspectable supporting arguments, and develop research plans informed by established workflows and unresolved evidence. We describe a corpus-scale system and evaluate scientific retrieval and knowledge-intensive question answering. With the answering model fixed, LKM retrieval improves accuracy by 9.30%, 4.20%, and 14.69% on ChemBench, PubMedQA, and SciBench, respectively. By connecting knowledge access to scientific reasoning and action, LKM provides a common foundation for discovering relevant research, reusing scientific knowledge, and coordinating cumulative inquiry across researchers, agents, and research cycles.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27297
PDF
-
UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation
2026-09-23 02:42:34Yutai Duan, Yahui Zhao, Zhangti Li, Yu Ma, Zhenfeng Qi, Shaoyang Yuan, Jing Fan, Jie LiuAbstract
Enterprise data agents must preserve organization specific semantics, not just translate questions into queries. We present ChinaUnicom DataAgent (UniDataAgent), an ontology grounded system for reusable question-to-report analysis that separates semantic acquisition from online execution. Ontology Acquisition and Validation stage (OAV) builds versioned enterprise ontologies from metadata, business knowledge, and supporting materials through expert authored business skills, constrained generation, question verification, and selected expert review. Question-to-Report Execution (QRE) stage retrieves semantic contracts for each question, coordinates skills and data tools, validates results, and produces evidence linked reports. Across 27 enterprise tables and roughly thousands of metric types, ontology construction took a few hours instead of about one week manually. It took just a few minutes to generate the reports, instead of several working days. Ontology grounding achieved 95.0\% strict accuracy on real business questions, versus 72.5\% for document RAG, especially on structured and compositional tasks. The system has already been deployed to generate cost savings and has the potential to be replicated in other enterprises.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27257
PDF
-
Meet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge Lattices
2026-09-23 01:45:23Yuze Ren, Shaoheng Fan, Tao Wang, Yabo Yan, Han HanAbstract
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.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27225
PDF
-
XLOG: A CUDA-Native Engine for Neurosymbolic Integration
2026-09-23 01:08:36Levi Dubrovin, Nikita Pospelov, Kirill SabitovAbstract
xlog is a CUDA-native logic programming engine integrating neural perception with deterministic Datalog, probabilistic inference, and epistemic world views through a typed frontend and provider-owned CUDA runtime. Its reasoning modes share device data planes, but their execution boundaries differ: ordinary Datalog and exact inference are host-orchestrated, while certified resident recursive and Monte Carlo sampled cores record zero tracked host-device transfers before a bounded terminal receipt. The probabilistic path supports end-to-end gradients through GPU knowledge compilation from provenance to CNF to Decision-DNNF, exact weighted model counting, and backward gradients. A final smoothed circuit is certified against its source formula before caching or evaluation. Circuit caching yields a 2.74x MNIST-addition training speedup; a worst-case-optimal join subsystem yields a 27.96x geometric-mean gain over xlog's binary-join baseline. MNIST-addition accuracy matches Scallop's (0.9561 versus 0.9468), but no per-epoch speed claim is made because baseline epoch time varies with CPU quota. In five hub-skewed triangle-counting cases, the Souffle-to-fused-xlog execution-time ratio rises from 0.88x at 150k edges, where Souffle is faster, to 5.54x at 1.2M; fused peak device allocations are 85-1,033 MB versus 3,287-44,979 MB for the materializing arm. Exact inference is correctness-equivalent to but slower than ProbLog2. On a public video benchmark, a proximity predicate trained only through symbolic credit replaces hand-set geometry at unchanged held-out accuracy; within Event-Calculus rule search it fails ten-fold cross-validation and does not transfer on a leak-free split. On a maritime corpus, weighted clauses beat crisp selection by 0.065 F1, with the result reproduced by one chronological training pass.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27203
PDF
-
Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences
2026-09-23 00:18:36Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Hoang-Loc Cao, Phuc Ho, Truong Thinh Nguyen, Van Pham, Hung CaoAbstract
Multimedia verification requires not only accurate decisions but also traceable evidence, reliable human correction, and safe reuse of prior experience. Existing systems often lack explicit mechanisms for revising intermediate reasoning or preventing harmful knowledge transfer. We present SEMV (Self-Evolving Multimedia Verification), a self-evolving multi-agent framework that treats provenance-bearing arguments as the interface between evidence, reasoning, human contestation, and memory. SEMV combines arena-based quantitative bipolar argumentation (A-QBAF), causal and scoped revision, and verification-gated memory consolidation with explicit conflict retention. On COSMOS benchmark, SEMV achieves 91.88% accuracy versus 89.10% for the strongest comparable baseline. Verified memory reduces negative transfer from 5.7% to 0.2%. On CTR benchmark, constructed from reviewer contestations, scoped causal revision corrects 96.7% of initial errors while saving 52.8% compute. MV2026 Grand Challenge dataset further supports evidence-grounded, temporally consistent reporting. These results show that SEMV can evolve through verified experience while keeping accumulated knowledge and subsequent decisions traceable, revisable, and contestable.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27175
PDF
-
HiRE: Hindsight Reward Editing for Policy Finetuning
2026-09-22 21:04:10Haoyi Niu, Zhengtao Han, Yufeng Ji, Zhongyu Li, Koushil SreenathAbstract
Pre-trained robot policies always require finetuning to adapt to specific environments. Reinforcement Learning (RL) offers high performance potential because it improves action optimality rather than simply mimicking data. However, such potential depends heavily on reward quality. Sparse rewards lack process feedback, human-designed rewards are costly and biased, and semantic rewards from foundation representations are often not control-centric. We propose Hindsight Reward Editing (HiRE), a training-free framework to break this reward bottleneck. HiRE bridges the broad knowledge of foundation representation models with physical control awareness, by contrasting successful and failed trajectories in hindsight. It calibrates foundation representation models by identifying "trap states" that are predicted as high-rewarding states yet eventually result in failure, and vice versa. HiRE explicitly penalizes these traps while boosting rewards for critical successful states. This approach can be flexibly compatible with any foundation representations and RL algorithms. Experiments show that HiRE consistently outperforms other reward recipes by delivering dense, control-aware feedback that prevents value function collapse and reward hacking, thereby achieving superior sample efficiency, stable policy updates, and higher performance ceilings, e.g., at least 3x performance of the base policies. Qualitative results are at this https URL .
Abstract (translated)
URL
https://arxiv.org/abs/2609.27068
PDF
-
ChipMEM: Verification-Grounded Memory for EDA Agents
2026-09-22 21:03:30Abdulrahman AlRabah, Joshua Mabry, Dilek Hakkani-T\"ur, Abdussalam Alawini, Hamid Shojaei, Kartik Hegde, Sandesh AdhikaryAbstract
Large language model (LLM)-based agents use Electronic Design Automation (EDA) tools to generate and revise register-transfer-level (RTL) designs under synthesis and verification feedback. Recent methods learn from this feedback by distilling reusable skills from execution traces or by training on rewards derived from EDA-tools. Both methods are typically evaluated on the tasks that produced the experience. Repeated access to benchmark feedback on the same task can reward task-specific revision rather than creating reusable knowledge that transfers. We introduce ChipMEM, a verification-grounded memory layer for EDA agents. It combines cross-task procedural memory with within-trajectory statistical guidance. Its procedural component distills and stores a skill only after it passes synthesis, simulation, or formal checks, rather than relying on model self-assessments. A Bayesian component maintains hierarchical Beta estimates over tool-call outcomes and ranks recovery strategies that succeeded under comparable errors. A common adapter applies the same memory interface to RTL optimization and testbench-generation agents while preserving each domain's tools and acceptance criteria. We measure performance on training tasks and evaluate whether learned skills transfer to unseen tasks. On RTLRewriter-Bench, under matched model and tool settings, ChipMEM produces equivalence-passing outputs on 39/54 scored designs versus 35/54 without memory; on the 49-design short suite, mean area improvement is 8.69% versus 5.66%. On held-out CVDP tasks, ChipMEM with a frozen procedural library achieves 20/20 accepted outcomes versus 18/20 without memory in a single evaluation per setting.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27067
PDF
-
Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms
2026-09-22 18:30:09Sahil Pardasani, Madhusudan SinghAbstract
Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple choice benchmarks, treating it as a recognition problem. We instead prompt five open weight LLMs to generate kinship terms in three non Western languages (Hindi, Tamil, and Korean) across two communicative tasks and pair this with a matched option-supported selection baseline. On identical relation language cells, GPT OSS120B selects the correct term in 90.67% of 75 valid cells but produces an accepted term in 36.00% of the corresponding attempts; Llama 3.370B shows the same pattern (77.92% versus 24.24%). Since the four-option condition displays the candidate terms and does not require script production, the difference is interpreted as an evaluation format gap rather than direct proof that lexical knowledge is intact. On explicitly specified L3 prompts, accuracy varies sharply, from GLM-5.1 at 72.29% to Llama-3.370B at 24.24%. The paternal-lineage advantage is language specific; it is large in Hindi but weak or reversed in Korean, while Tamil shared-term pairs provide a control for measurement variation. These results show that culturally specific kinship generation remains difficult even when the relationship is explicitly stated and motivate generation-based evaluation alongside multiple-choice testing.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26942
PDF
-
Know Your Body: A Harness for Direct and Self-Improving Robot Control with VLMs
2026-09-22 17:57:19Zeyu Lou, Yanhong Zeng, Yong Wang, Chenyang SiAbstract
A general-purpose vision-language model can understand a task goal without knowing how a particular robot's motion and functional parts produce the intended effect. We introduce KnowBody, a harness that makes these action-relevant body relations explicit, queryable, and revisable while keeping the model weights frozen. Initialized from one off-task trajectory, a partial body model guides action selection and the interpretation of past interactions. New evidence refines the model, and knowledge dependent on revised body estimates is rechecked before reuse. Across 32 fixed-budget trials on four real-robot tasks, initialized KnowBody achieves 75% completion versus 25% for the native harness and requires fewer planner rounds on successful trials in tasks completed by both. With persistent updates enabled, planner rounds decrease by 29-53% from the first to the fifth recorded success.
Abstract (translated)
URL
https://arxiv.org/abs/2609.28530
PDF
-
Discovery-Driven Integration of Disjoint Tables via Text
2026-09-22 16:22:54Md Ataur Rahman, Dimitris Sacharidis, Oscar Romero, Sergi NadalAbstract
Integrating heterogeneous datasets within data lakes is a critical challenge, particularly for semantically related tables that lack the explicit attributes needed to be joined. We study Discovery-Driven Integration, where the relevant sources and their missing relational structure must be discovered before integration. In this setting, unstructured text provides the evidence that connects otherwise disjoint tables. The fundamental challenge is to discover the relationships at a fine-grained level that connect individual rows from different tables through specific sentences. We formalize this task as Text-Mediated Join Path Discovery and propose a horizontal bidirectional cross-attention architecture called LOKI Latent-space Optimization for Knowledge Integration) that learns contextualized representations of table rows and sentences. Through a global table-text contrastive objective, fine-grained row-sentence associations emerge without explicit local supervision. Existing multi-modal discovery methods largely retrieve coarse-grained column-text associations, whereas integration systems assume supplied row-text links, schemas, or queries. LOKI instead transforms these implicit associations into explicit, interpretable join paths, organizes them into relation-consistent groups, and materializes them as typed integrated tables with sentence-level provenance. Comprehensive evaluations on real-world benchmarks demonstrate that LOKI consistently outperforms state-of-the-art multi-modal data discovery approaches, and materializes typed integrated tables with 0.982 macro typed-pair precision while being up to 40 times cheaper in LLM API cost than direct prompting.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26658
PDF
-
Knowledge Pull Requests for Continual Document Authoring
Abstract
We introduce Knowledge Pull Requests (KPRs), a framework for continual document authoring that makes each change interpretable. Documents require ongoing revision as new knowledge surfaces from other sources, languages, or times, but existing approaches either edit with no account of what knowledge changed or regenerate from scratch. A KPR integrates new knowledge into a document by extracting claims, filtering and routing them to sections, and flagging conflicts with existing content, producing a ChangeLog that separates what knowledge changes (claim proposal) from how the text changes (document diff). We evaluate KPRs on revising Wikipedia across languages and updating query-driven reports on RAGTIME. KPRs integrate more information and better preserve existing content than rewriting from sources or regenerating from scratch, while adding the most information per token generated. A KPR-revised article also grounds question answering better than a frontier model with search, which does not surface knowledge documented only in other languages.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26634
PDF
-
Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models
2026-09-22 15:46:23David Torres-Moreno, Jorge Hermosillo-ValadezAbstract
Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction. In this study, we are interested in understanding how LLMs leverage abstract semantic knowledge in natural language inference (NLI), which requires sophisticated linguistic capabilities to interpret implicit meanings, contextual conceptual relationships, and semantic connections between words and phrases. To this end, we propose a methodological framework for constructing new semantic knowledge at a higher level of abstraction, which we define under the notions of semantic compatibility and incompatibility for NLI. In this framework, the meaning of the lexical-semantic relations between the premise and the hypothesis is reconfigured to achieve a more flexible semantic network that induces different reasoning paths in LLMs. These new pathways show a consistent pattern of responses that allows agreement on a single response. The results demonstrate that our proposal allows to discover and compensate for LLMs' semantic knowledge gaps in NLI, achieving significant improvements in accuracy, exceeding 10% for some models, and in particular for the non-entailment class. It is essential to note that LLMs need structured knowledge and not just more data to bridge reasoning gaps. Our hybrid approach directs attention to overlooked word relationships, allowing models to synthesize missing information. We believe that the future lies not in increasing model size, but in creating a semantic scafolding that mimics the flexibility of human thinking. Hopefully, our proposal will enable the development of more robust agents and interpretable reasoning, guiding AI toward reliable language understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26610
PDF
-
Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying
2026-09-22 13:19:16Wooyoung JungAbstract
Building automation systems are increasingly represented as semantic knowledge graphs (KGs) using ontologies such as Brick and ASHRAE 223P, creating a machine-readable substrate for artificial-intelligence applications. One promising application is translating natural-language questions into SPARQL (text-to-SPARQL), which would let building operators query these graphs through language agents, but progress is limited by the scarcity of large natural-language/SPARQL benchmarks. This paper presents Build2SPARQL, a large-scale benchmark for building KGs generated by a KG-grounded pipeline: SPARQL queries are produced and validated entirely by graph-traversal code, while large language models generate only the natural-language questions, keeping query correctness independent of model behavior. The pipeline mines six query-pattern families -- linear chains, branching, UNION, aggregation, OPTIONAL, and attribute-filtered -- and phrases each query across five vocabulary registers. Applied to 201 building KGs (180 Brick, 21 ASHRAE 223P), it yields 6,136 executable SPARQL queries and 30,680 questions. A two-rater human validation of 300 questions found 98.8% semantic fidelity, 98.8% naturalness, and 84.0% operational plausibility. A retrieval-augmented evaluation across three open-weight language models raised exact-match accuracy from 0.2-20% (zero-shot) to 56-65% (three-shot retrieved).
Abstract (translated)
URL
https://arxiv.org/abs/2610.00224
PDF
-
Designing and Analysing Argument Mining Pipelines: Towards a Comprehensive Assessment
2026-09-22 12:46:29Siddharth Bhargava, Sara Tonelli, Patricia Mart\'in-RodillaAbstract
Argument Mining (AM) transforms natural language into its underlying argument structures. This transformation is typically realized through a sequence of AM tasks that form an end-to-end AM pipeline. However, AM approaches often differ in how they conceptualize these tasks, making direct comparisons between them difficult and opaque. This calls for a more nuanced, task-level analysis of AM approaches to enable clearer comparison and assessment. This work presents a preliminary meta-study that systematically reviews several state-of-the-art end-to-end AM works and analyzes their pipelines through a triple-perspective framework---a linguistic, computational and domain perspective---to understand how the pipelines model arguments as structures, computes them, and integrates domain knowledge. We further propose a general design to the linguistic and computational perspectives, illustrating how key AM tasks are designed for modeling and computation of argument structures. Our proposed framework lays the groundwork for methodology-centered descriptions across AM approaches, facilitating deeper understanding and more systematic comparisons in future research.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26338
PDF
