Knowledge_Graph
-
Megrez: A Knowledge-Guided Agent for Formal Mathematics over MK Set Theory
2026-11-10 05:42:16Tiancheng Xu, Wensheng YuAbstract
General-purpose coding agents equipped with proof-assistant tools have shown strong performance on standalone competition problems, yet cumulative textbook formalization inside a low-resource mathematical library still faces three obstacles: aligning textbook concepts with library declarations, keeping long-horizon search synchronized with live proof states, and integrating locally verified proofs reliably into a growing codebase. We present Megrez, a knowledge-guided formalization agent for Rocq libraries built on Morse--Kelley (MK) set theory. Megrez coordinates a general coding agent through three mechanisms: (1) a source-rebuildable knowledge graph merging formal declarations, compiler references, and curated metadata to support retrieval via Chinese aliases, concept clusters, proof dependencies, and multi-lane full-text ranking; (2) a feedback-driven 1--5 tactic short-burst proving loop paired with a goal-local branch ledger and exponential-interval structured reflection; and (3) a three-check acceptance pipeline (statement fidelity, axiom auditing, and full builds) coupled with a multi-corpus Provider stack and a candidate-bound recoverable batch state machine. Deployment and evaluation on a point-set topology corpus demonstrate effective cross-chapter formalization and scalable premise retrieval.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13613
PDF
-
The WoW: A Large-Scale World Knowledge Corpus for Full-Lifecycle LLM Training
2026-11-10 02:56:20Tianze Sun (Harbin Institute of Technology), Yongyao Duan (OpenCSG), Sam Chen (OpenCSG)Abstract
Existing Chinese educational corpora often suffer from fragmented coverage and a lack of systematic organization. In this paper, we propose WoW (\textbf{Wo}rld Kno\textbf{w}ledge), a large-scale dataset designed for the full-cycle training of foundation models. The construction of this dataset is driven by an Educational Knowledge Graph, which serves as a taxonomic backbone for the systematic collection and completion of missing educational modules across all levels. Compared to previous versions, this iteration provides enhanced systematicity, superior quality, and a larger scale, while incorporating multimodal signals and supporting every stage of model development. Experiments demonstrate that WoW significantly improves model performance across diverse benchmarks. To facilitate community research, we further provide an interactive platform for graph-based data selection and retrieval.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13487
PDF
-
From Process Models to Composable Agentic Workflows: Combining BPMN, Agents and Enterprise Knowledge
2026-11-09 20:18:32Christian Fillies, Jan Fillies, Frauke Weichhardt, Gay Anne Wood-AlbrechtAbstract
LLM-based agents can reason, use tools and collaborate. However, coordinating increasingly complex agentic applications becomes difficult to understand, monitor and improve. Decisions distributed across prompts, tool calls and application logic make workflows implicit. We introduce **Recursive Capability Composition**, enabling agents to execute business processes and expose them as reusable Agentic Tools. This paper presents a BPMN-based approach to Agentic Workflows, combining explicit orchestration with autonomous reasoning. SemTalk BPMN models are transformed into executable workflows using a LangGraph/Pregel runtime. Agentic Tasks introduce LLM reasoning at selected activities, while conventional BPMN controls process flows, deterministic decisions, system interactions and human approvals. Agentic Participants provide reusable interfaces for agent behavior or other executable processes. BPMN orchestration makes multi-agent systems more understandable and manageable. Explicit process models provide developers and operators with a shared view of workflow structures and execution progress, facilitating debugging, monitoring and optimization. Enterprise agents also need organization-specific context. Process Models and Knowledge Graphs describe activities, participants, information objects, decisions and relationships between processes. They provide structured knowledge of how an organization operates, supporting informed agent decisions and actions. Our contributions are threefold: 1. **Model-Driven Execution:** Transforming BPMN models into executable Agentic Workflows. 2. **Recursive Capability Composition:** Exposing agents and executable business processes as reusable tools for other agents. 3. **Enterprise Context:** Using Process Models and Ontologies to provide organization-specific knowledge for agent reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13196
PDF
-
Evidence-Grounded Iterative Reasoning for the Diagnosis of Diffuse Cystic Lung Diseases
2026-11-08 07:48:04Haoqing Li, Jun Shi, Tou Li, Xianmeng Chen, Rui Wang, Yating Peng, Qiwei Jia, Li Gao, Qianyi Chen, Hong An, Ruoyun Ouyang, Xiaowen HuAbstract
Overlapping imaging manifestations complicate the differential diagnosis of Diffuse Cystic Lung Diseases (DCLDs), while limited annotated data constrain supervised model development. Multimodal Large Language Models (MLLMs) can integrate imaging and clinical information, but their diagnostic reasoning remains limited by incomplete volumetric perception and insufficient grounding in disease-specific evidence. We propose DCLDs-EIR, an evidence-grounded iterative reasoning framework coupling diagnostic hypothesis refinement with multimodal evidence acquisition and verification. Multiview renderings of predicted lung and cyst segmentations characterize global cyst distributions and initialize the differential diagnosis. Competing hypotheses guide axial CT inspection to identify local findings that, together with clinical context, inform retrieval from a disease-specific knowledge graph. Accumulated patient observations and retrieved knowledge are jointly assessed for diagnostic support and refutation to revise the diagnostic state. Updated hypotheses and unresolved distinctions guide subsequent inspection, forming a feedback loop between evidence acquisition and hypothesis verification. Multicenter evaluation demonstrates that DCLDs-EIR consistently improves diagnostic accuracy over baselines and enables traceable differential diagnosis through explicit links between diagnostic hypotheses, patient observations, and disease-specific knowledge.
Abstract (translated)
URL
https://arxiv.org/abs/2611.12981
PDF
-
Graph Visualizations in Prompts for Knowledge Graph Question Answering
2026-11-06 14:55:29Luiz do Valle Miranda, Andreas L. Opdahl, Grzegorz J. NalepaAbstract
We study when and how multimodal input improves knowledge graph question answering (KGQA) in large vision--language models. Using a controlled evaluation over 1,500 WebQSP and CWQ questions and six VLMs within a fixed KGQA pipeline, we compare text-only prompting against text-plus-graph visualization at the per-question level and analyze performance changes as a function of reasoning complexity, model size, and image layout. Adding a graph image yields an average gain of 1.85 F1 points, driven by strong precision improvements on low-complexity questions (+4.65 F1). Mixed-effects and regression analyses show that these multimodal gains do not depend strongly on model scale, but are highly sensitive to graph layout: image-only settings sharply degrade performance, hierarchical Graphviz layouts outperform less organized renderings, and decomposing large subgraphs into separated paths yields the largest improvements. Taken together, the results indicate that visual prompting primarily aids KGQA by enhancing prediction precision in low-complexity contexts, provided that visual design respects cognitive and perceptual constraints. To optimize both accuracy and inference efficiency, we argue for adaptive visual prompting policies that selectively append diagrams to small, visually sparse subgraphs with well-structured layouts, avoiding unnecessary visual clutter and token overhead on complex queries. We conclude by relating these findings to a visual notation design theory, outlining how principled diagram encoding can guide future multimodal VLM prompting.
Abstract (translated)
URL
https://arxiv.org/abs/2611.12938
PDF
-
FinEvolveKG: Controlled and Attributable Prompt Evolution for Financial Knowledge Graph Construction
2026-11-05 19:44:51Abhinav Arun, Jayita Bhattacharyya, Fabrizio Dimino, Bhaskarjit Sarmah, Stefano PasqualiAbstract
Financial institutions construct knowledge graphs (KGs) from shared SEC 10-Ks to serve risk analysis, portfolio management, and investment research, whose analytical needs differ. Extraction must adapt without fragmenting shared grounding, typing, and temporal rules. Hand-authored persona prompts and fine-tuning add cost. Weight-free prompt optimization offers an alternative, but unconstrained evolution of a monolithic prompt can rewrite shared rules alongside persona guidance, obscuring changes and complicating review. We introduce FinEvolveKG, a KG-construction harness separating reusable general and persona-policy blocks and mechanically confining GEPA, a reflective prompt optimizer, to the designated block. During persona adaptation, the approved general block remains byte-stable and every optimizer edit is localized to a separately versioned persona policy. A dual objective balances generic temporal-KG quality with persona-relevant facts, motifs, and multi-hop connectivity. We evaluate five mutation scopes on ticker-disjoint 10-K splits, with three seeds for the persona-conditioned arms (v3-v5) across three personas. On the three-seed mean, the complete two-stage block-constrained workflow (v4) improves over the frozen prompt baseline (v1) by 19.4-30.9% and over the tested unconstrained full-prompt workflow (v5) by 2.2-6.4%, leading v5 on both objective components and winning all nine paired-seed comparisons with the lowest seed variance in every persona. Without further optimization, v4 also exceeds v5 across all evaluated out-of-distribution (OOD) shifts. An SME audit supports using the generated triplets as ground truth; a blinded two-SME audit favors v4 over v5 in 70.1% of contrast-enriched judgments. These results show that mechanically attributable evolution can coexist with strong empirical performance, without attributing the gains causally to the boundary.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08643
PDF
-
Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation
2026-11-05 17:12:58Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh JeiraniAbstract
Large language models (LLMs) are increasingly used in biomedical and cognitive neuroscience, but their ability to reason reliably over heterogeneous knowledge graphs (KGs) remains unclear. We benchmark five LLMs (GPT-5.1, Gemini 2.0 Pro, Llama 3, Qwen, and BioGPT) across five KGs: DrugBank, NeuroSynth, Cognitive Atlas, Brain Map, and GDPKG. We introduce a multitier query dataset to evaluate reasoning depth and factual accuracy under KG-aware (graph-grounded) and KG-agnostic conditions. Inter-annotator agreement was substantial, with Cohen's kappa of 0.781 (range: 0.753-0.807) and Fleiss' kappa of 0.77. Results show that general-purpose models, particularly GPT-5.1 and Gemini 2.0 Pro, generally outperform domain-specific models on multi-hop and high-level reasoning tasks, although performance declines as query complexity increases. KG grounding reduces hallucination rates across all evaluated models. Contrary to our initial hypothesis, domain-specific models do not consistently outperform general-purpose models on specialized tasks without graph grounding. These findings highlight the value of combining broad language-model capabilities with structured domain knowledge. We provide practical guidance for selecting LLM-KG integration strategies based on task complexity and computational constraints, and discuss hybrid neurosymbolic architectures for personalized medicine, cognitive disorder diagnosis, and explainable AI.
Abstract (translated)
URL
https://arxiv.org/abs/2611.08315
PDF
-
Generate-then-Rank: Learning Symbolic Goal Interpretation for Embodied Agents
2026-11-05 11:05:53Jisen Lei, Huizhi LiangAbstract
Goal interpretation is to translate a natural language instruction into a formal symbolic goal that a planner can execute. It is critical for embodied agents because any error here propagates to every downstream planning and action step. Doing it well requires both generating suitable candidates and reliably selecting among them. We present a two-stage generate-then-rank approach to Goal Interpretation in the Embodied Agent Interface (EAI). First, supervised fine-tuning adapts a Large Language Model (LLM) to EAI's output convention. Second, Candidate-Output Ranking from Errors (CORE) learns preferences over complete outputs from the model's own generated alternatives. We conducted experiments on the household scenes of the Embodied Agent Interface Benchmark. Multiple open source LLMs including DeepSeek-V3 chat, DeepSeek-Reasoner, and Qwen2.5-7B and Qwen2.5-72B were evaluated. The proposed method outperformed the baseline models including LLMs with simple prompting, chain-of-thought, and knowledge graph based approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07825
PDF
-
Bridging Structure and Semantics: Knowledge Graph Verification via Triple-to-Text Alignment
2026-11-05 10:19:27Ziang CuiAbstract
Semantic accuracy is an important dimension of knowledge graph quality. Graph-based scoring methods exploit relational structure, while textual representations allow classifiers to draw on knowledge encoded by pre-trained language models (PLMs). We present GenVer, a generative verifier that scores triples using both their serialized form and generated natural language representations (NLRs). A triple-text alignment procedure selects training pairs for a sequence-to-sequence generator; a BERT-based classifier then combines features from each triple and its generated NLR. On four FactFB variants, constructed from FB15k using perturbed negative triples, GenVer obtains the highest classification accuracy among the evaluated baselines, ranging from 88.56% to 91.52%. The experiments suggest that generated representations can help triple classification, while the case analysis also exposes semantic drift and high-confidence errors.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07780
PDF
-
ThermoLLM: LLM-Based Multi-Zone HVAC Control with a Spatiotemporal Context
2026-11-05 03:34:18Kirtan Bhatt, Xiachong Lin, Matthew Amos, Flora D. Salim, Wen HuAbstract
Multi-zone HVAC control is a spatial decision problem in which indoor thermal evolution and control decisions depend not only on outdoor conditions and internal heat gains but also on zone layout, physical adjacency, and delayed thermal interactions across the building. Recent LLM-based HVAC controllers have shown that prompt-based control is feasible. However, these methods produce inconsistent results, are difficult to generalize, and experience control-latency issues. Their performance also relies heavily on numeric reward values, textual feedback, or unstructured retrieval, which limits their ability to make control decisions that account for zone dynamics and thermodynamics. No existing LLM-based methods have used building semantics and dynamics, together with rolling history, as the centre of the LLM context while testing and comparing HVAC control performance with existing LLM-based HVAC approaches. This paper presents ThermoLLM, an LLM-based HVAC control framework tested in a multi-zone building environment. Spatiotemporal context grounding is a main component of ThermoLLM, which uses a spatial knowledge graph derived from Brick-style building semantics and linked with recent observations from a rolling history. We evaluate ThermoLLM against standard control methods and recent state-of-the-art baselines in a five-zone building environment across six climate-season scenarios. ThermoLLM consistently achieves the best energy-comfort trade-offs and outperforms all evaluated baselines in the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) rankings across all six scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2606.22911
PDF
-
Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair
2026-11-05 02:29:58Tung-Wei Lin, Gabe Fierro, Han Li, Tianzhen Hong, Pierluigi Nuzzo, Alberto Sangiovanni-VinentelliAbstract
Knowledge graphs often contain missing or inconsistent facts that undermine the applications built on them. Schema validation detects such violations but does not identify which of several valid repairs recovers the intended graph. External corpora can supply the evidence needed to identify the intended repair, but retrieving from them is costly and not always successful. We propose a framework for selective retrieval in iterative graph repair. An LLM repair agent explores and edits the graph, while a router controls its access to a researcher agent that retrieves external evidence. We extend a violation-injection framework to generate cases with multiple compatible violations and known reference repairs. The agent's repair outcomes on these cases provide supervision for training the deployment-specific router. On two building-automation datasets, researcher access improves repairs for some violations and degrades them for others, with effects differing across deployments. The router uses fewer repair-time tokens than always enabling access in all six evaluation suites. It achieves higher repair $F_1$ than always disabling access in five of six suites.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07342
PDF
-
KG-Neighbor: Knowledge-Guided Neighborhood Construction for Embedding Visualization
2026-11-04 23:54:02Chang Won Kim, Jaewook Lee, Haeun Min, JunNyeong Jeong, Minwoo Sim, Barom Kang, Kyohoon JinAbstract
In embedding visualizations, nearby instances are interpreted as semantically related, although neighborhoods derived from input embeddings may not reflect content relationships. Neighborhood-based dimensionality reduction (DR) methods can propagate this limitation by optimizing layouts from embedding-based neighborhood graphs. We propose Knowledge-Guided Neighborhood Graph Construction (KGN), which represents relational knowledge derived from each instance as a set of knowledge graph (KG) triples. It uses the degree of triple sharing as pairwise semantic evidence to adjust embedding distances and reconstruct the top-k neighborhood graph; neither KG extraction nor neighborhood construction uses class labels. We also introduce IDProfile (IDP), which interprets residual mismatches by independently assessing whether the source content supports the assigned class label and the neighborhood-majority class. Across eight text and image dataset-encoder conditions, we characterize KGN over the full guidance-strength sweep and four KG similarity measures. Across this sweep, the maximum NMI and LT_2D each exceed the corresponding kNN baseline in all eight conditions, with the largest gains reaching 0.68 and 1.35, respectively. The gains and the extent of neighborhood reconfiguration vary across conditions and are larger under encoder conditions with lower kNN baseline scores. The IDP analysis shows that the largest reductions are concentrated in Placement Issue candidates, whereas Label Issue and Unresolved Case instances account for a larger share of the remaining review set. These results indicate that KGN can narrow the evaluated gap between embedding-based neighborhoods and content-supported semantic relations, while IDP shows that a residual mismatch should not automatically be interpreted as a projection failure.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07246
PDF
-
ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs
2026-11-04 13:20:51Jyotin Goel, Abhinav Arun, Tejas Prakash Agarwal, Bhaskarjit Sarmah, Stefano PasqualiAbstract
Graph-based retrieval-augmented generation (GraphRAG) answers questions by retrieving over a knowledge graph built from a corpus. Yet retrieval strategies are designed around the structure their own construction pipeline produces, and whether they survive a change of construction is rarely tested. We study this cross-construction portability: whether one retrieval procedure, with no construction-specific schema, relation names, or retuning, stays effective when the graph is built differently. We introduce ArcRAG, which induces a query-local graph interface at inference time (the node labels, relation descriptors, and property keys reachable from the entities a question names), plans multi-hop traversals against it, and executes and repairs them as Cypher. We build each of the MuSiQue, HotpotQA, and TriviaQA corpora as a schema-guided graph (typed nodes, a closed relation set, source provenance) and as an open-information-extraction graph (untyped nodes, free-text relations), with the retriever's configuration fixed across them. We compare against a construction-agnostic Direct-Cypher agent, ablate each stage across retry and pass budgets on both graph families, and compare with results reported for prior GraphRAG systems, most of which design retrieval together with their own graph construction. Across the two constructions, we find that retrieval need not be co-designed with the graph: query-time interface induction keeps a construction-agnostic retriever effective when the construction changes, although construction still shapes absolute accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06481
PDF
-
ModalSearcher: Weaving Visual Evidence into Autonomous Cross-Modal Deep Search
2026-11-04 08:14:50Zhihan Yin, Ruyi Li, Chengyu Fang, Yifeng Yao, Nonghai Zhang, Pengfei Xiong, Terry Zhang, Huishuai Zhang, Dongyan ZhaoAbstract
Static and incomplete parametric knowledge limits the performance of multimodal large language models on novel-knowledge and knowledge-intensive tasks, especially those requiring multi-hop evidence acquisition. Existing multimodal agentic search methods often fix visual evidence at the input or a predefined trajectory position, making it difficult for agents to select search modalities as their information needs evolve and to handle complex real-world queries. We define this capability as autonomous cross-modal search: an agent chooses among direct reasoning, text-to-text search, text-to-image search, and reverse-image search, actively introduces visual evidence when appropriate, and switches between and integrates modalities across multiple hops. We propose ModalSearch-Pipeline, a scalable procedure for constructing an interleaved multimodal knowledge graph. It samples paths with diverse depths and modality compositions and uses backward question construction to obscure entity names and image targets that would expose reasoning shortcuts while retaining necessary disambiguating clues, yielding text-only, image-initialized, and arbitrarily interleaved multi-hop problems. We train the ModalSearcher Agent with supervised fine-tuning and reinforcement learning in a live Web environment, and construct ModalSearch-Bench. Experiments show that ModalSearcher-8B improves average accuracy by 16.2 points over Qwen3-VL-8B under the same agentic workflow across five multimodal knowledge-intensive QA benchmarks, with consistent gains on independently constructed active visual-search benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2611.06131
PDF
-
When Does Better Confidence Improve a Knowledge-Graph Audit?
2026-11-04 03:12:37Zehao Lin, Kai Chen, Xixuan Hao, Erenkai Zhu, Chunyu Li, Helan HuAbstract
Confidence estimates guide human review in LLM-built knowledge graphs, but better error prediction can yield little improvement in an audit. We study this gap through repairability, selection headroom and label validity. Modelling non-adaptive auditing as budgeted covering, we characterise the minimal decision-relevant error statistics and bound the regret of scalar-preserving first-order planning by a structural mass $\Delta^{\mathrm{cl}}$. We simulate ideal repair against benchmark-aligned labels for five extraction configurations and two cross-document graphs on Re-DocRED, followed by frozen confirmation on test and replication on 500 hash-selected training documents. On the held-out cross-document graphs, an error-rate $\times$ fan-out queue leaves 3.98-4.74 percentage points more errors than a joint model with the same actions. By comparison, opening shared actions for that joint planner reduces residual errors by 0.89-1.43 points relative to its own fact-only plans, in point estimates. Equivalence between joint and independent-block models remains inconclusive. Generic LLM verification improves three of four model-budget configurations on each held-out set. LLM adjudication identifies possible benchmark omissions.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05877
PDF
-
Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex
2026-11-03 23:50:38Andrew Miracle, Phyl Georgiou, Christine Okoth, Ese MondayAbstract
Organizations accumulate evidence in conversations, documents, decisions and relationships, but they act on interpretations: judgements assembled from several observations, resting on assumptions, and revised as circumstances change. Existing retrieval, knowledge graphs and agent memory keep the records and lose the interpretation. We propose a four-layer architecture, Signals, Domains, Claims and Dimensions, in which interpretations persist with their justifications and standing, a truth-maintenance network revises that standing as evidence changes, and validated, versioned Dimensions position interpretations on named axes. We call the result a shared organizational cortex. In a registered retrieval experiment, the Dimension term gains 0.028 nDCG@10 (p = 0.002). In system-level comparisons, the full retrieval configuration improves nDCG@10 by 0.081 over Signals-only and 0.053 over graph-augmented Signals-only retrieval (both reported p < 0.001). The architecture gives organizations a persistent, revisable basis for shared judgement.
Abstract (translated)
URL
https://arxiv.org/abs/2611.05753
PDF
-
CREDO: Evidence-Conditioned Credit Assignment for Temporal Reasoning Agents
2026-11-01 06:46:51Yue Leng, Shengtao Wen, Xiang Chen, Xinyi Zeng, Yu Tian, Sheng-Jun HuangAbstract
Temporal Knowledge Graph Question Answering (TKGQA) requires language model agents to retrieve evidence, select relevant facts, and perform multi-step temporal reasoning. However, the trajectory-level outcome signal in GRPO does not explicitly distinguish the quality of intermediate decisions: downstream failures can penalize useful evidence acquisition, while identical rewards in all-failed groups eliminate the relative outcome signal despite differences in intermediate progress. We propose Credit Redistribution with Evidence-Driven Opportunities (CREDO), which uses intermediate evidence to recover local supervision, including in all-failed groups, and determine where outcome supervision acts. CREDO assigns positive stage-level credit through comparisons among rollouts of the same question and uses retained answer overlap as an opportunity proxy to shift part of the outcome-policy weight toward reasoning and answering. The framework preserves terminal rewards and trajectory-level advantages, while redistribution conserves total outcome-policy weight per trajectory. Following the public evaluation protocol of prior work, CREDO raises Overall accuracy from 78.0% to 82.4% and Multiple accuracy from 55.0% to 65.6% on MultiTQ relative to the strongest published baseline in our comparison. On TimelineKGQA, it raises cross-KG accuracy from 30.9% to 36.4% relative to our reproduced baseline via direct transfer to ICEWS Actor under matched training and evaluation settings.
Abstract (translated)
URL
https://arxiv.org/abs/2611.01643
PDF
-
ImplicitHop: Evaluating knowledge integration across context and memory
2026-10-30 02:44:51Alexander Detkov, Dashiel Karish, Matthew Oleynikov, Matt ThomsonAbstract
The ability to integrate new information and deduce its consequences is central to learning, understanding, and reasoning in large language models (LLMs). Whether information arrives during training or in-context, models must not only store local facts, but propagate their long-range implications globally. To explore information integration in LLMs, we introduce two complementary natural language benchmarks for large-scale evaluation of deductive reasoning as a function of inference depth. The first is a formal graph benchmark enabling controlled evaluation over a wide range of graph topologies and integration tasks; the second is a knowledge composition benchmark grounded in real-world knowledge graphs. We use these benchmarks to compare knowledge integration from information encoded in context versus information encoded in model weights during pretraining, evaluating a set of open models implicitly, without chain of thought. We find that accuracy decays sharply with increased composition length for both pretrained and in-context knowledge. Information presented in-context, however, substantially outperforms deduction over information encoded in weights. These results quantify a fundamental limitation of current models with direct implications for prompt-based control of agent behavior and for continual learning strategies, and they provide a foundation for developing training, prompting, and integration methods that support deeper reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41169
PDF
-
FieldGuideRAG: Image-Grounded GraphRAG for Fine-Grained Recognition with Vision-Language Models
2026-10-29 20:58:20Jiacheng Ding, Yanliang Qi, Cong Guo, Peihua MaiAbstract
We present FieldGuideRAG, a training-free GraphRAG method in which a vision-language model, or VLM, recognizes fine-grained species by comparing the query with real photographs stored on the nodes of a knowledge graph. Multimodal GraphRAG systems describe each entity in text, and text conveys little of the visual detail that separates look-alike species. Our graph stores one photograph on every species node and links each species to its relatives, its geographic range and its ecological facts. A frozen VLM verifies the query against the photograph of each candidate node. FieldGuideRAG fuses the verification scores with the range edge and answers questions about the organism from the fact edges of the verified species. On CUB-200, a Wikidata graph and four iNaturalist domains, the node photograph improves verification over the species name on every graph, while text descriptions add little. Verification of the candidate pool exceeds a SigLIP retriever by up to 16 points, the range edge adds 7 to 19 points on iNaturalist, and answering from fact edges is correct on up to 89.5% of 28,820 ecological questions. The verification scores also detect queries whose species is missing from the graph. Graphs, prompts and code will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40971
PDF
-
FIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge
2026-10-29 17:13:45Yunbai Zhang, Yunyi Gao, Han-Tai ShiaoAbstract
Financial AI workflows that reuse investor knowledge need persistent memory that integrates observations across sources and periods without losing identity or provenance. In a knowledge graph, recurring observations may use different surface forms, fragmenting relationship histories and preventing evidence from accumulating. We introduce Fusion and Identity Registry for Memory Evolution (FIRME), a registry-anchored memory graph that reconciles incoming observations to persistent canonical relationships and retains their source, time, and context. Within periods, rule-based fusion links investor-call discussions to portfolio cash-flow signals, directly or through a fixed product-topic ontology. Across periods, canonical identities and persistent aliases direct recurring observations to the same relationship history; deterministic updates summarize reinforcement, inactivity, and reactivation. We evaluate FIRME on proprietary investor-call and cash-flow records and on S&P 500 earnings-call transcripts. Compared with a historical registry that retains canonical identities and semantic fallback but omits alias memory, FIRME increases final-period Correct Match Rate by 7.8-12.1 percentage points across four dataset-backend settings under a fixed-judge and fallback-review protocol. A blinded human audit of 200 incoming observations per setting finds Correct Match Rate gains of 9.0-16.5 points and reattachment-recall gains of 22.5-29.0 points, with higher observed merge precision in all four samples. A separate audit finds valid evidence paths for 293 of 300 outputs from full within-period fusion in the investor-call setting. Extraction-faithfulness and round-trip diagnostics assess source grounding and preservation of extractor-derived graph content.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40482
PDF
