Knowledge
-
AgentOnto: Ontology-Guided LLM Agents for Enterprise Data Analytics
2026-10-16 11:22:38Dayan Pan, Bincheng Zuo, Xiaojian Wang, Daogang Zhang, Jingyuan WangAbstract
Enterprise data analysis requires agents to connect analytical requests with knowledge distributed across databases, business documents, and existing example tasks. Without an explicit representation of this knowledge, an agent may produce incorrect analytical results and cannot reliably incorporate feedback. We present AgentOnto, an ontology-guided LLM agent for enterprise data analytics. AgentOnto organizes heterogeneous enterprise knowledge into an ontology that directly guides analysis and incorporates confirmed feedback. Iterative Ontology Preparation further improves the ontology through self-generated analysis tasks. We evaluate AgentOnto on two public data sources. AgentOnto substantially outperforms representative methods, while module-level evaluations confirm the effectiveness of ontology construction, analysis, and updating. A real-world deployment further demonstrates its practical value in enterprise analytics. These results demonstrate that explicitly constructing, using, and updating enterprise knowledge supports reliable and adaptable data analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23317
PDF
-
Self-Reflective Chain-of-Thought : Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
2026-10-16 11:14:52Fabian Broszio, Michael Hoffmann, Adrian PaschkeAbstract
Large language models (LLMs) can generate fluent outputs that lack source support or conflict with local operational constraints. We introduce Self-Reflective Chain-of-Thought (SRCoT), a modular architecture that organizes generation as a closed Retrieve--Reflect--Revise loop. SRCoT separates environment state, persistent knowledge, accumulated experience, and short-term memory into provenance-labeled stores. BM25 retrieval supplies local context; subsequent passes expose intermediate drafts, missing-information markers, follow-up queries, and optional claim--evidence mappings. These artifacts inform retrieval, revision, clarification, or abstention decisions. We examine the architecture through qualitative, trace-based case studies in two fully synthetic settings: emergency medical services and Munich-Sim, an emergency-operations simulation. Local prototype runs on an Apple M4-family laptop with 128 GB memory illustrate source-labeled documentation, explicit gap marking, and structured dispatch-style outputs. The traces also reveal provenance-assignment errors, incomplete evidence coverage, and unsafe assumptions that remain possible despite prompting constraints. These cases demonstrate report-level inspectability and local execution, not comparative superiority, hallucination reduction, clinical validity, or operational safety. The architecture separates retrieval and control from the model interface, but behavior across different models remains to be evaluated. SRCoT is a research proof of concept requiring human review, with its principal contribution lying in an inspectable control procedure rather than a new model.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23311
PDF
-
SimOPD: Relational Knowledge Transfer for On-Policy Distillation
2026-10-16 11:10:21Kai Tang, Xing Zheng, Haobo Wang, Guangcheng Zhu, Shenzhi Yang, Zhengqing Zang, Yingfan Ma, Bowen Song, Weiqiang WangAbstract
A key challenge in on-policy distillation (OPD) is extracting effective supervision from teacher knowledge. Supervision from token probabilities may underutilize internal knowledge, while direct hidden-state matching forces the student to shift to the teacher's feature space and complicates cross-architecture transfer. Inspired by contrastive learning's use of relationships between instances, we propose \textbf{SimOPD} to transfer teacher internal knowledge through response similarities. Specifically, SimOPD uses paired memory banks of student-generated responses to extract supervision from the teacher's internal representations as similarity distributions. The student then matches these distributions within its own representation space, retaining representational freedom and removing the need for cross-model projection. Extensive experiments show that SimOPD improves the overall average over the strongest baselines by up to 2.6 and 3.1 percentage points in same- and cross-architecture settings.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23306
PDF
-
Designing for Imperfect Prompts: A Simulation-Based Evaluation of an LLM-Based Enterprise Data Assistant Using Knowledge Graphs
2026-10-16 11:07:04Niklas Wagner, Alexander M\"adcheAbstract
Enterprise data assistants using large language models (LLMs) promise democratized data access in organizations. Yet in our real-world deployment within the CFO unit's data lake at an industry partner, we observed that business users frequently pose imperfect prompts that include domain-specific vocabulary and lack schema references or structural information. This Design Science Research study examines automatic resolution using a semantic mediation layer. We design and evaluate two design variants: schema-based mediation via semantic similarity, and knowledge graph-based mediation leveraging an automatically constructed knowledge graph from the data lake. Our simulation-based evaluation using real-world data, supported by LLM-as-a-Judge assessments and human validation, shows that knowledge graph-based mediation outperforms the schema-based approach in Precision, Recall, F1, and preserving user intent. We propose a design principle for knowledge graph-based mediation, demonstrating that structured knowledge representation bridges user intent and database structure and guides the design of enterprise data assistants across skill levels.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23304
PDF
-
Who Pays for Efficient Inference? Confidence-Based Small-to-Large LLM Routing Across Tasks and Languages
2026-10-16 10:23:41Md Sabbir Hossen, Anichur Rahman, Pabon Shaha, Airin Afroj Aishi, Andrew H. Sung, Md Shohel RanaAbstract
Small-to-large language model routing can reduce inference cost by escalating difficult inputs while retaining easier ones on a smaller model. Its success, however, depends on identifying examples that benefit from escalation, and the reliability of confidence across multilingual tasks remains unclear. We present a systematic evaluation of confidence-based routing across three model families, four languages, and three task types, covering 72 model, dataset, language, and scale configurations and 42,288 predictions. We compare global confidence routing with random routing, equal-quota confidence routing, and an oracle upper bound. Confidence identifies beneficial escalations on the Belebele reading comprehension and SIB-200 topic classification datasets, with mean correction-detection AUCs of 0.612 and 0.705. At 50% escalation, it improves over random routing by 1.40--4.67 percentage points on Belebele and 2.54--5.63 points on SIB-200. In contrast, the mean AUC on the MMLU-ProX-Lite knowledge and reasoning dataset is only 0.510, and routing provides no consistent improvement over random selection because small models often remain highly confident while incorrect. Global confidence routing also creates language escalation gaps up to 30.33 percentage points, whereas equal-quota routing removes this disparity with little aggregate accuracy cost. These results show that confidence routing is task-dependent and can allocate computation unevenly across languages. Code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.23249
PDF
-
What LLMs Do in the Shadows: Reading Context Reliance from the Unembedding Dark Space
2026-10-16 09:21:49Alexandra Kuleshova, Andrey Volodichev, Daria Kotova, Alexey ZaytsevAbstract
Detecting faithfulness hallucinations in large language models (LLMs) is crucial for their safe deployment in high-stakes domains. Recent approaches address this by contrasting contextual against parametric knowledge utilization, yet measuring context reliance typically demands noticeable overhead, such as materializing attention maps, running additional forward passes, or training auxiliary probes. In this work, we show that context reliance can be estimated by projecting hidden states onto the dark space - directions that compose weakly with the unembedding matrix. Beyond its recognized function as an initial-token attention sink, we show that this subspace actively mediates context processing, and that its share of hidden-state norm - termed the Dark Matter Ratio (DMR) - provides a direct score of context utilization. Pairing DMR with a parametric knowledge score yields DarkLens, a lightweight faithfulness detector operating strictly within a single forward pass. Evaluated across three QA and summarization benchmarks on six open-weight LLMs (4B-13B parameters), DarkLens matches or outperforms a wide range of baselines without requiring extra forward passes or probe training.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23182
PDF
-
Knowledge-Guided Distributional Prompt Learning with Visual Hierarchy for Zero-Shot Anomaly Detection
2026-10-16 09:10:18Jiyul Ham, Seongho Yoon, Yonggon Jung, Sangjae Lee, Jun-Geol BaekAbstract
Zero-shot anomaly detection (ZSAD) aims to detect anomalies in previously unseen classes using auxiliary images, with applications such as industrial visual inspection and medical imaging. Recent vision-language-model-based approaches improve ZSAD by aligning textual and visual representations, while distributional prompting further models prompt variability for unseen categories. However, existing methods do not explicitly combine normality-referenced distributional modeling with hierarchy-specific prompt specialization, limiting their ability to model anomalous semantics relative to normality while addressing both image-level detection and fine-grained localization. We propose Hierarchical Knowledge-Guided Distributional Prompt Learning (HiDist), a normality-referenced hierarchical distributional prompt framework for ZSAD. HiDist models each prompt token with a diagonal Gaussian distribution and generates stochastic prompt variations through Monte Carlo sampling. Rather than learning normal and anomalous distributions independently, anomalous prompt distributions are parameterized as deviations from learned normal references, explicitly encoding their dependency. The resulting distributions are specialized into global and local representations for image-level detection and pixel-level localization, respectively, while an adapted global visual representation guides hierarchical alignment. Experiments on seven industrial and medical datasets demonstrate strong cross-dataset performance across anomaly detection and localization tasks. Extensive ablation and representation analyses further support the effectiveness of the proposed distributional modeling and hierarchy-specific representation learning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23172
PDF
-
Algorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence
2026-10-16 08:59:42Jian Yao, Zhiyao Zhang, Yichen Li, Xingyu Wu, Kay Chen TanAbstract
Can algorithms be learned and evolved as models, rather than repeatedly redesigned as programs? We explore this question by introducing Algorithm Modelization, a new paradigm that turns iterative algorithms into trainable models. Its central idea is to regard algorithm execution trajectories as computational experience: by learning how algorithmic states evolve over iterations, a model can internalize the knowledge embodied in existing algorithms, reproduce their computational behaviors, and further evolve beyond them through training. As a first realization of this paradigm, we modelize iterative optimization as an autoregressive process, where preceding generations constitute the computational context for generating the next population. We develop a dimension-independent population-temporal architecture to capture both population interactions and iterative dynamics, together with an imitation-to-surpassing learning framework that first acquires algorithmic knowledge from heterogeneous teachers and then improves the resulting optimizer directly through optimization feedback. The modelized optimizer consequently goes beyond reproducing individual algorithms: it consolidates heterogeneous search knowledge into a single trainable model, achieves stronger optimization capability through subsequent improvement, and generalizes its acquired knowledge across problems and substantially larger unseen dimensions. More fundamentally, Algorithm Modelization makes algorithmic capability accumulable through learning, where new algorithms and problem-solving experience can become training resources for progressively improving the model. Our results establish a promising path from manually designed algorithms toward general algorithm models that learn, generalize, and evolve from computational experience.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23161
PDF
-
Foundation Models for Autonomous Space Robotics: Architectures, Physical Adaptation, and Validation
2026-10-16 07:42:06Zizhe Wang, Jia Deng, Xin Lu, Zehao Jia, Yi Huang, Yao Zhu, Jianing LiAbstract
Space robots must interpret tasks and act despite unfamiliar dynamics, difficult sensing conditions, and limited opportunities for human intervention. Foundation models offer reusable perceptual and behavioral knowledge, but their value depends on how that knowledge reaches physical execution. This critical review follows space-specific requirements through perception, prediction, planning, and action to deployment and validation, emphasizing orbital manipulation and proximity operations. Terrestrial comparisons establish benefits of particular pretraining stages and model interfaces; their transfer to space dynamics and constrained onboard operation remains insufficiently tested. Event cameras offer timely motion observations across strong illumination contrasts, while spiking neural networks provide possible routes to sparse local computation. We examine how sensor degradation, state estimation and computing choices affect feedback and recovery. Higher action throughput need not yield fresher feedback; lower processor power can also coexist with higher energy per inference. We organize validation as an iterative sim-to-ground-to-space pathway, connecting physical tests with telemetry-based diagnosis and closed-loop revalidation. A satellite-capture example links observations to approach, contact and recovery, while a corresponding protocol separates generalization from adaptation with limited target-domain interaction. These comparisons identify what models already contribute and the physical evidence needed to support autonomous space operation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23068
PDF
-
Adaptation of Computer Use Agents to New Software with User Manuals
2026-10-16 06:44:56Chulhoon Yoon, Kyungri Park, Jinyeong Yun, Daeyun Jeong, Sukmin Yun, Woohwan JungAbstract
Recent advances in multimodal foundation models have significantly improved the ability to operate real-world software through graphical user interfaces (GUIs) using visual observations and natural language instructions. However, maintaining strong performance on unseen applications remains challenging, as practical tasks often require long-horizon procedural knowledge and application-specific operation patterns. In addition, constructing executable tasks and collecting corresponding trajectories for training still heavily rely on human-annotated data, incurring substantial cost. In this paper, we propose MAGE (Manual-augmented computer use AGent Execution and learning), a framework that leverages user manuals as a scalable source of procedural knowledge to improve both inference and training. During execution, MAGE retrieves task-relevant manual content and uses a planner to generate explicit procedural guidance for CUAs. To further account for the discrepancies between manuals and actual GUI environments, such as version differences or user settings, MAGE also adapts the agent policy through environment interaction. During training, MAGE converts manuals into executable task-plan pairs and uses the plans to guide environment rollouts toward task-relevant states; the resulting trajectories are then used to optimize the policy without human-authored demonstrations. This unified design enables effective utilization of manuals for both task execution and training, reducing reliance on human-authored training data. Experimental results across six applications demonstrate improvements in task success rates over strong baselines, highlighting the effectiveness of manual-guided planning and policy adaptation in new software environments. We provide the code and reproduction scripts at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23012
PDF
-
NL2SQL with Iterative Self-Refinement
2026-10-16 05:39:18Anjali Vemula, Akshat DasulaAbstract
Bridging the gap between human intent and machine logic remains a critical challenge in data access for non-technical users, yet Large Language Models (LLMs) remain unreliable: they hallucinate schema elements, generate syntactically invalid queries, or fail to capture user intent. These limitations are especially critical in domains such as insurance, where KPIs, regulatory constraints, and legacy relational systems demand high precision. We introduce a multi-agent, persona-driven NL2SQL framework that combines (1) domain relevance detection, (2) schema-grounded knowledge construction, (3) KPI-aware SQL synthesis, (4) syntax-level self-repair using sqlite execution feedback, and (5) semantic consistency checking via SQL-to-NL reverse engineering. Our system significantly reduces query hallucination and improves semantic fidelity compared to direct LLM prompting. Evaluated on 60 queries (50 from a HuggingFace text-to-SQL dataset and 10 custom domain queries), the system achieves 90% correctness using Mistral across seven coordinated LLM calls showing that this approach can substantially increase the reliability of NL2SQL pipelines in high-stakes environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22968
PDF
-
DriftTTS: One-stage Single Step Text-to-Speech via Generative Drifting
2026-10-16 05:31:38Jaehyun Ahn, Dohyun Kim, Heeseung KimAbstract
Text-to-speech models built on score matching and flow matching produce natural speech, but only by calling the decoder many times, which makes synthesis slow. Existing ways to cut the number of calls either distill from a multi-step teacher or add a stage on top of a pretrained model, leaving single-step TTS without a pretrained TTS model unexplored. We question whether pretraining a TTS model is necessary, and propose DriftTTS, which adopts generative drifting, an objective that moves iterative sampling from inference into training. Drifting assumes samples of fixed shape, whereas speech has variable length; we address this issue with segment drifting. On LJSpeech, DriftTTS matches the multi-step quality of Matcha-TTS and RapFlow-TTS in a single decoder call, while being faster. To our knowledge, this is the first application of generative drifting to text-to-speech.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22960
PDF
-
The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level Falls
2026-10-16 02:33:51Lucas Resck, Jingyi Sun, Qianli Wang, Isabelle Augenstein, Anna KorhonenAbstract
Chain-of-Thought (CoT) faithfulness matters for monitoring, explaining and safely deploying large language models, yet it has been studied mostly in English. Languages differ in level, the amount of text available to learn from, so models know less in lower-resource languages, which may change how much they rely on their reasoning. To our knowledge, we are the first to relate CoT faithfulness to both resource level and task type (knowledge- or reasoning-intensive). On parallel multiple-choice questions from Multilingual Massive Multitask Language Understanding (MMMLU) in eight languages, faithfulness rises as resource level falls on knowledge-intensive tasks but not on reasoning-intensive ones, a gap that points the same way across four models and several faithfulness measures. We propose, and find support for, the Reliance Hypothesis: models rely more on their reasoning when they cannot recall the answer, as in lower-resource languages on knowledge-intensive tasks. Model confidence partly explains the effect of resource level, but not the knowledge-reasoning gap. Languages in which models are less confident rely more on reasoning, yet less confident answers within a language do not, a Simpson's paradox. In lower-resource languages, models rely on their reasoning for more answers, not more strongly for each. CoT monitoring may therefore be most informative in lower-resource languages, where it is least often validated.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22841
PDF
-
PAC-KD: Pathology-Aware Compositional Knowledge Distillation for Respiratory Sound Classification
2026-10-16 02:09:01Li Xiao, Weiping Tu, Youqiang Zheng, Dan ChenAbstract
Respiratory sound classification distinguishes four categories: Normal, Crackle, Wheeze, and Both (crackle and wheeze). Existing knowledge distillation transfers four-class predictions without explicitly exploiting shared respiratory events, potentially limiting the transfer of event-specific knowledge across individual abnormal classes and the Both class. We propose PAC-KD, a pathology-aware compositional knowledge distillation framework that learns crackle and wheeze presence through two dedicated specialists. Their complementary knowledge is transferred to a unified four-class student, enabling it to effectively capture pathology-specific attributes while preserving class-level discrimination. Furthermore, stable conflict calibration adaptively regulates specialist guidance according to its consistency with classification supervision, mitigating potential supervision conflicts. Experiments on ICBHI and SPRSound achieve Scores of 65.28\% and 89.54\%, respectively, outperforming strong knowledge distillation baselines on both datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22826
PDF
-
Replay Pruning and Few-Bit Integer Inference for Hardware-Efficient Speed-Sign Recognition
2026-10-16 01:41:06Se Un Park, Kyungkeon Chung, Huigeol Kim, Junyoung ParkAbstract
Speed-limit sign recognition on an automotive camera system-on-chip (SoC) must fit a detector and a classifier (the reader) into the memory, arithmetic, and energy budgets of the device. In our two-stage recognizer, the detector, a YOLO-family network with ReLU and hard-sigmoid operators, is compressed by channel replay: an iterative pruning cascade identifies the channels to remove, the recorded deletions are replayed on the original task-trained network, the parent, and one continuous knowledge-distillation recovery follows. On a YOLOv5n, replay removes 60.3% of the parameters at the accuracy of the parent and, in validation mAP50-95 over five matched seeds, outperforms iterative pruning and training from scratch, and its per-step variant (per-step replay) is the most accurate pruning method. On a YOLOv8n, replay and per-step replay outperform every other method and the unpruned parent. The reader, a five-layer CNN with 18k parameters, and the post-processing of the YOLOv5n and YOLOv8n heads use integer arithmetic only. With 4-bit weights and 8-bit activations (W4A8), the reader matches FP32 accuracy in 12.1 KB of on-chip memory, and an executable streaming model reproduces the INT8 class predictions of its runtime on all 9,850 test crops. On a Jetson AGX Orin, INT8 is faster than FP16 only in the implicit formulation of TensorRT, and the replay detector runs fastest on the deep-learning accelerator (DLA). Trained on public data only, the combined system of 0.72 M parameters recognizes 95.2% of the signs of a held-out automotive camera at 90% precision and 94 frames per second.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22811
PDF
-
Prune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning
2026-10-16 01:09:22Mohamed Shaaban, Mohamed ElmahallawyAbstract
Fine-tuning large language models (LLMs) on proprietary records enables domain adaptation but introduces two challenges: (i) privacy leakage of memorized private data, such as personally identifiable information (PII), and (ii) balancing private data removal with utility preservation. Existing defenses, including data sanitization and differential privacy, often degrade performance, while privacy-neuron editing lacks a PII-free reference to distinguish identity-specific neurons from those supporting useful text. We propose JEPA-Prune, a post-hoc neuron pruning framework guided by a model trained exclusively on PII-free views. Alongside the fine-tuned private model, JEPA-Prune, trains a public model on surrogate and masked views of the same records using a joint-embedding predictive architecture (JEPA), capturing domain knowledge without identifiers. A cross-model representation probe quantifies deviations between private representations of leaked records and this PII-free reference. Integrated gradients and a scale-invariant specificity score then identify PII-responsive neurons, which are pruned without retraining. Experiments show that pruning just 1.6% of neurons reduces PII inference accuracy by up to 7.4x and PII extraction recall by up to 13.9x, while keeping unseen-text perplexity within 16% of that of the unpruned model for most LLMs. In contrast, privacy-neuron editing increases perplexity by at least 26x.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22792
PDF
-
StoBasket: Joint Upsell and Cross-Sell Optimization for Contribution Margin
Abstract
Retail recommenders rank relevance, but retailers earn contribution margin: an upsell earns the margin difference over the item it replaces, whereas a cross-sell earns its full margin. We introduce joint stochastic basket editing, a formulation in which one policy selects replacement and addition offers for an existing basket, values them by expected incremental contribution margin, and couples them through displayed-offer, accepted-offer, and joint-acceptance response channels. To our knowledge, it is the first formulation in which upsell and cross-sell responses are coupled; prior separable treatments are its zero-coupling special case. In real-data-calibrated simulations on five public basket datasets, StoBasket captures essentially all attainable offer margin: within 0.5% in every default-price setting and within 0.7% when the true response lies outside its model family. Correct economic accounting is the broadest gain: margin-weighted popularity leaves up to 11% of attainable margin unrealized, and a published next-basket recommender leaves 11-52%. Joint selection adds 10.2% of attainable margin on Instacart, where premium tiers and add-ons are strongly linked. When offers pay only together, the best heuristics lose 64% while exact search stays within 0.5%. For a structured subclass, we characterize when staged policies fail and give an exact optimizer that solves every tested real basket in 0.13 ms median and at most 111 ms. Profit saturates long before prediction accuracy: a correctly structured predictor trained on 5,000 randomized sessions comes within 0.06% of perfect prediction, while a signal-free one loses 38%. The same estimates yield a decision-aware market-basket analysis whose cost does not grow with association order.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22768
PDF
-
Graph Serializations for Reasoning LLMs: A Study Across Knowledge Extraction and Structural Reasoning
2026-10-15 23:12:21Julien Yu, Mihaela Bornea, Avirup Sil, Katrin KirchhoffAbstract
The way a knowledge graph is serialized as text for inclusion into LLM context can substantially affect downstream LLM performance, with prior work reporting tens of percentage points variations across formats. However, existing studies consider only a limited set of representations and predate frontier reasoning models, which now offer stronger reasoning, instruction-following, and long-context capabilities. We evaluate 15 graph representation formats across nine frontier LLM configurations on ontology-based knowledge extraction and structural graph reasoning tasks. While knowledge extraction is relatively insensitive to different serialization formats, the choice of the optimal format for structural reasoning tasks significantly affects accuracy. We demonstrate that the optimal representation choice depends on model, query, and task and propose to approach graph serialization as a dynamic orchestration decision.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22734
PDF
-
CoLU: Confidence-Weighted Layerwise Unlearning for Large Language Models
2026-10-15 22:51:35Jingkai Guo, Ziyi Zhao, Chaitali Chakrabarti, Deliang FanAbstract
Large language model (LLM) unlearning aims to forget certain information while preserving others, without retraining from scratch. SoTA methods such as NPO, SimNPO, and SatImp balance forgetting and retain through whole model fine-tuning, while FOM-UL explores selective layer updates. Prior works show that suppressing target information can damage retained knowledge. This trade-off can vary across layers even under the same unlearning loss. In this work, we propose Confidence-Weighted Layerwise Unlearning (CoLU), which combines a novel confidence-weighted forgetting and retain regularization while updating a single selected transformer layer, rather than the whole model for unlearning. To reduce CoLU compute cost, we further propose Brief Layer Screening (BLS), which uses a newly defined normalized forgetting-retention (NFR) score to first rank layers through a brief unlearning trials using a subset of forgetting dataset and fewer epochs. BLS pre-selects top-k ranked layer candidates, which will then be fully profiled using full data analysis. BLS is proven to reduce the runtime of CoLU by 60.2-79.7% with almost the same performance. On TOFU dataset, CoLU improves both forgetting and retention over NPO, SatImp, and GA-based FOM-UL in all six TOFU settings, and over SimNPO in five of the six settings. On MUSE Books and News datasets, CoLU achieves the highest retained KnowMem and the PrivLeak closest to zero among the compared SOTA unlearning methods. CoLU presents a new record performance in both unlearning and retain in most settings up to date. Moreover, across the measured settings, average CoLU GPU memory usage is 77.4% to 79.5% lower than full-model unlearning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22721
PDF
-
Multimodal Filesystem Memory For Long-Horizon Embodied Agents
2026-10-15 21:56:00Chloe Su, Jiahan Li, Zhenting Qi, Chaoran Cheng, Haoyu Chen, Sejoon Jun, Weirui Ye, Yilun DuAbstract
Agents operating over long horizons need an effective memory that allows them to reuse their experience throughout long interactions. If the entire history of an interaction is retained, it becomes difficult to find the relevant experience, while compressing it into summaries may result in the loss of visual and spatial details that are required later on. We present \textbf{MFM}, a multimodal filesystem memory architecture that keeps complementary types of agent memory. \textbf{Episodic memory} stores the observations, actions, and outcomes, and \textbf{spatial memory} associates experiences with locations. \textbf{Semantic and procedural memory} build up general knowledge and reusable methods of acting, and \textbf{working memory} holds the current plans. MFM makes use of searchable textual records to connect these different representations to the underlying multimodal episodes. The agents are able to find previous experiences by means of contextual cues and to examine the original observations in order to recover details that are missing from their textual descriptions. Through consolidation, the agents convert experience into higher-level knowledge and procedures while still keeping references to the original episodes. In the case of long-horizon Minecraft and computer-use tasks, MFM leads to improved performance with three base models. With GPT-6-Astra, MFM completes \emph{Mine Diamond from Scratch} and reaches 16 out of 24 milestones on the \emph{Ender Dragon} task, as against 12.7 for the best baseline. On CUABench-KiCad it attains a mean reward of 0.440, as compared to 0.400 for the best baseline and 0.267 in the case of no persistent memory.
Abstract (translated)
URL
https://arxiv.org/abs/2610.22686
PDF
