# Research Papers — 2026-09 · bundle page 266 of 266

> Full-text markdown of papers #13251–13298 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-09/page/266
[← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/265.md)

### BeamRMX: Radiation-Pattern-Driven Learning for Generalizable Beam Radio Map Prediction and Beam Management

Authors: Yue Zhang, Xiucheng Wang, Wenshuo Chen, Nan Cheng
Published: 2026-09-01
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2609.00615v1

The evolution toward sixth-generation (6G) wireless networks is driving larger antenna arrays and highly directional multi-beam transmission, making accurate knowledge of beam-dependent spatial coverage important for beam management and environment-aware network operation. Radio maps (RMs) provide such a representation, yet conventional RM prediction assumes omnidirectional or transmitter-level radiation. In beamformed multiple-input multiple-output (MIMO) systems, one propagation scene instead gives rise to many configuration-dependent beam radio maps (BeamRMs), creating challenges in beam representation and generalization. Existing methods either condition prediction on beam descriptors or use beam maps as auxiliary inputs to generic architectures. We propose BeamRMX, which, to the best of our knowledge, is the first dedicated framework to treat the spatial radiation pattern as the primary BeamRM query and learn how scene geometry transforms it into the received power field. XBase learns multiscale interactions between the radiation query and scene geometry, while an optional Evidence Adapter uses a few cross-configuration BeamRMs from the same scene. Matched-domain and zero-shot experiments show consistent gains over deterministic and diffusion baselines, including mean absolute error reductions of 26.1\% on unseen scenes and 47.8\% on an unseen configuration. Cross-configuration evidence further improves reconstruction and intra-sector beam refinement.

---

### Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics

Authors: Samuel Young, César Jesús-Valls, Kazuhiro Terao
Published: 2026-09-01
Categories: hep-ex, cs.CV
arXiv: https://arxiv.org/abs/2609.00611v1

Foundation models are increasingly being pursued in particle and nuclear physics, but existing approaches remain strongly tied to individual experiments through detector-specific architectures or pre-training objectives, limiting their reuse across sensing modalities. We show that a point cloud self-distillation framework yields a substantially more general sensor-level pre-training recipe. We show that the same refined architecture and objective can be independently pre-trained with minimal changes on three qualitatively different detector modalities: liquid argon time projection chamber (LArTPC), collider TPC, and water Cherenkov. Using 1,000 labeled images for downstream task adaptation, Panda V2 matches or exceeds specialized foundation-model baselines trained with orders of magnitude more supervision, matching state-of-the-art particle-clustering performance with 70x fewer labeled events on sPHENIX while substantially improving particle identification, and on LArTPC data matching Panda (arXiv:2512.01324) particle reconstruction with up to 1,000x fewer labels. Beyond reconstruction, simple linear probes reveal physically meaningful latent structure associated with particle causality and track curvature.

---

### Streaming4D: Accelerate 4D World Models via Block-wise Video Generation and Incremental Reconstruction

Authors: Xiaoyan Liu, Jiaxin Liu, Kangrui Li, Sifan Zhou
Published: 2026-09-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.00610v2

Current 4D generation paradigms are often bottlenecked by a sequential decoupling design: video is generated first, followed by 3D reconstruction, leading to high interaction latency. This limits applications in interactive real-time scenarios. To this end, we propose \textbf{Streaming4D}, a tightly coupled synchronous pipeline that integrates block-wise autoregressive video generation with incremental 3D reconstruction. Unlike traditional frame-by-frame emission and delayed geometry recovery, Streaming4D generates temporal video blocks and immediately triggers reconstruction for each completed block, enabling parallel execution between synthesis and geometric updates. This approach allows the world representation to evolve online with the video stream, reducing feedback latency while preserving geometric fidelity. We instantiate \textbf{Streaming4D} using a Self-Forcing-style autoregressive generator and an incremental reconstruction backend. Experiments show consistent runtime improvements across resolutions on a single RTX 4090 (1.24$\times$ speedup), while maintaining high-quality 4D geometry and multi-view consistency.

---

### Investigating Assistant Bias in LLM User Simulators Using a Role Vector

Authors: Daeheon Jeong, Yoonjoo Lee, Eugene Choi, Sinie van der Ben, Juho Kim
Published: 2026-09-01
Categories: cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2609.00608v1

LLM-based user simulators are increasingly used to evaluate autonomous agents at scale, in place of costly human evaluations. Despite this promise, these simulators exhibit "assistant bias," a tendency to cooperate and pursue task goals. They rarely reproduce the frustration or disengagement that real users exhibit, compromising evaluation validity. Prior work outlines that this bias is baked in during model training, which role-playing prompts fail to override. We analyze this bias from model activations, extracting a user role vector by contrasting how the model represents user versus assistant perspectives on the same dialogue. We observe two findings: (i) the user direction is identifiable in activations, elicits user-like behaviors, and captures characteristics distinct from assistant traits; and (ii) although user-role activation associates with simulation realism and steering strengthens it, it can exaggerate user behaviors and override individual user profiles. Together, our findings provide a representation-level analysis of LLM user simulators, confirming that assistant bias is structurally identifiable and that user behavior can be directionally analyzed.

---

### Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning

Authors: Miso Kim, Georu Lee, Seungwon Jeong, Woojin Lee
Published: 2026-09-01
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2609.00605v1

Machine unlearning for large language models (LLMs) often assumes that a pre-defined forget set matches what the model has memorized, but this frequently breaks in realistic privacy settings where the original training data is inaccessible. We term this gap forget-set misalignment and identify two cases. In Under Unlearning, the forget set omits memorized information and leakage persists. In Out-of-Knowledge Unlearning, the algorithm is driven to "forget" knowledge the model never learned, perturbing parameters and degrading utility. Using gradient-level analysis, we show these behaviors arise from misaligned unlearning targets rather than specific optimization choices. We then propose CONfession-to-Forget-Set (CONFS), a data-blind framework that constructs model-aligned forget sets by eliciting and formalizing the model's memorized knowledge. Across synthetic, multimodal, and real-world benchmarks, CONFS approaches Gold-standard performance on several metrics and achieves a competitive forgetting-utility balance, while preserving utility better than other data-blind forget-set constructions.

---

### Topological Steering

Authors: Benoît Guérand, Tan Minh Nguyen
Published: 2026-09-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.00597v1

With the rapid rise of large language models (LLMs), controlling undesirable model behaviors has become increasingly important. Existing behavioral control methods typically intervene directly in activation or feature space, but such approaches can be sensitive to outliers, distributional shifts, noise, and other local perturbations. Motivated by Topological Data Analysis (TDA), which captures global rather than purely local structure, we propose Topological Steering, a new framework for steering LLM behavior through the topological representation of activation spaces. Using persistence diagrams, our method connects activation-based steering with TDA and enables more robust behavioral control. We show that Topological Steering consistently modifies LLM behavior across multiple model families and model sizes.

---

### SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems

Authors: Rui Yang, Junjie Xu, Zhengyu Liu, Neil Fendley, Yang Hong, Ziyang Li, Yinzhi Cao
Published: 2026-09-01
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.00595v1

Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating failures that local checks may miss. Without an execution-level view, a multi-agent setting can easily be mistaken for evidence of a genuinely multi-agent security effect. We thus systematize MAS security through an execution-centered analysis of 197 works, covering six interaction interfaces, four adversary positions, seven system-level risks, and eight recurring attack paths. We introduce an A-I-R framework that organizes attacks by adversary position, interaction interface, and resulting system-level risk, unifying otherwise fragmented attack mechanisms across MAS. We organize defenses through a five-part contract covering path target, observation, intervention, trust boundary, and recovery, and identify path closure and recovery as key challenges. We audit 44 evaluation and benchmark works and identify open challenges in isolating interaction effects, designing comparable and diagnostic metrics, supporting reuse across MAS designs, and evaluating open-system operation. Together, these findings motivate an interaction-aware view of MAS security: trace attacks end to end, test whether defenses close those paths, and evaluate system-level effects with appropriate counterfactuals.

---

### BrainDiff: Longitudinal Report Generation for Multimodal Brain MRI

Authors: Krish Patel, Peirong Liu
Published: 2026-09-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.00593v2

Neuroradiologists rarely read a brain MRI in isolation, yet automated brain-MRI report generation has been built almost entirely for single studies. Temporal analysis has been explored on chest radiography and chest CT, but to our knowledge, longitudinal reporting for brain MRI, where interval change is often subtle and spatially distributed, remains unaddressed. We present BrainDiff, the first longitudinal vision-language system for brain MRI. BrainDiff outperforms both frontier general-purpose and single-study neuroimaging models on the same patient pairs. Moreover, BrainDiff retains 91% of internal RadGraph-XL entity+relation F1 (rg_er) on an external, cross-hospital cohort. Beyond the system, we contribute three analyses. First, we identify two independent grounding levers: a counterfactual objective with prior-report dropout, which increases measured image reliance by ~47%, and a staged curriculum. Together, these interventions raise image reliance 2.5-fold from the baseline. Second, we provide a factorial over prior-report availability and image identity, isolating a visual contribution of +0.0387 rg_er, which grows when the prior report is withheld. Third, a cheap change-decodability test for candidate backbones shows that interval change is decodable far more weakly than single-study pathology (0.60 vs. 0.77 AUROC). Code is publicly available at https://github.com/jhuldr/BrainDiff.

---

### A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss

Authors: Suryaansh Jain, Rahasya Barkur, Vishal G, Ryan Rossi, Franck Dernoncourt, Jack Wang, Koustava Goswami, Nedim Lipka, Puneet Mathur, Samyadeep Basu, Seunghyun Yoon
Published: 2026-09-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.00591v1

An image may be worth a thousand words, but most captioning models describe it in only a few. Modern vision-language models produce fluent high-level captions, yet routinely miss the attributes, counts, textures, materials, and spatial relations that make an image visually specific. Recent multi-stage systems recover some of these details through generation, decomposition, verification, and rewriting, but they do so at the expense of substantially higher inference latency. We propose SimLoss, a reference-free embedding-space objective for single-pass fine-grained image captioning. SimLoss trains a vision-language model to align its projected hidden-state representation with a frozen image embedding through an InfoNCE contrastive loss, supplying a dense visual supervision signal before any text is decoded, and requiring neither human-written fine-grained captions nor pseudo-captions from a multi-stage pipeline. We instantiate it as SimLoss FFT, which backpropagates through a locally available embedding model, and SimLoss GRPO, which treats that model as a black-box reward. Compared with single-pass, multi-stage verification, reward-optimized, and perception-aware baselines, the fully differentiable fine-tuning variant, SimLoss FFT, achieves the highest precision while nearly matching the F1 score of the multi-stage method, all while retaining single-pass inference and running roughly 20 times faster than the multi-stage pipeline. The reward-based variant SimLoss GRPO attains the strongest recall. Together, these results show that embedding-space supervision can recover the quality of multi-stage verification at the latency of a single-pass captioner.

---

### CRAFT: Fine-Tuning Pre-hoc Explainability in AI-native 6G RAN

Authors: Pranshav Gajjar, Vijay K Shah
Published: 2026-09-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.00590v1

The next generation of mobile networks is envisioned as fully AI-native, with AI-RAN architectures embedding small language models (SLMs) to perform reasoning over real-time telemetry. The state-of-the-art training paradigms for telecom LLMs, exemplified by RANSTRUCT-style supervised fine-tuning (SFT) on curated instruction data, are limited to post hoc rationalization. Here, the explanations, when produced at all, are generated after or independently of the decision, leaving the decision process unauditable. Pre-hoc reasoning, where a causal reasoning trace is produced before the output label, is preferable, and the broader LLM reasoning literature has made real progress toward it via RL methods such as Group Relative Policy Optimization (GRPO). Here we observe that transplanting this recipe into the telecom setting runs into a cold-start barrier: SLMs either learn to output the desired format or learn to predict the label, but rarely both. We identify this barrier and propose CRAFT, which stands for Cold-start Reasoning Alignment via Fine-Tuning, a data-centric method to autonomously generate a verified dataset of (input, trace, label) triplets. CRAFT fine-tunes SLMs on this verified data using low-rank adaptation (LoRA), requiring substantially less compute and wall-clock time than GRPO-based methods. On the TRACTOR and IC xApp telecom datasets, CRAFT achieves up to 86.5% and 94.6% for accuracy and F1 with no parse failures, while direct GRPO and SFT+GRPO fail to exceed 28% and 53.5% F1 with multiple parse failures. We further show that CRAFT-initialized policies serve as a robust foundation for subsequent GRPO fine-tuning, as under diverse reward functions the performance remains consistent with no parse failures. Finally, we demonstrate that CRAFT consumes 59% less energy than GRPO-based baselines, making it a sustainable path to deployable, auditable AI in 6G RAN.

---

### Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation Reranking

Authors: Guangyu Chen, Boxuan Lyu, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura
Published: 2026-09-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.00588v4

Reranking methods, such as Minimum Bayes Risk (MBR) decoding and Quality Estimation (QE) reranking, have been widely used in modern neural machine translation (NMT) to select an output from a set of candidate hypotheses. However, the performance gains come at the cost of high inference latency. Existing acceleration methods target MBR decoding and reduce only the reranking computation, leaving QE reranking unaddressed and candidate generation---which can be the larger computational bottleneck---largely untouched. In this work, we propose Quit (Quantifying Uncertainty for Incremental Termination), a novel early-stopping strategy for the entire generation--reranking pipeline. Quit treats candidate generation as a sequential decision-making process under uncertainty. It incrementally generates and reranks candidates, stopping when the best reranking score stabilizes. Comprehensive experiments with three NMT models across 19 language pairs show that Quit achieves end-to-end speedups of $1.47$--$2.66\times$ for MBR decoding and $3.43$--$4.12\times$ for QE reranking while preserving automatic metric scores.

---

### Real-Time Neuromorphic Spectrum Intelligence Simulator

Authors: Navaneetha Krishnan Kamalakannan
Published: 2026-09-01
Categories: eess.SP, cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2609.00585v1

We present the Real-Time Neuromorphic Spectrum Intelligence Simulator (RT-NuSIS), a modular framework to study spiking neural network (SNN) and memristor-inspired agents for dynamic spectrum access under constrained energy budgets and adversarial conditions. RT-NuSIS couples leaky integrate-and-fire neuronal dynamics, memristive synaptic models, physics-informed energy-harvesting models (triboelectric and RF), and adversary models including jamming and Byzantine behavior. We formalize the simulator mathematically, prove boundedness, present a mean-field adversary threshold, analyze per-step complexity, and provide a reproducible benchmark harness for energy-per-inference, latency, and robustness metrics. The codebase is modular, deterministic by seed, and designed for large-scale event-driven simulations.

---

### Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Context using Brain Sensing

Authors: Alexandre Clin Deffarges, Nataliya Kosmyna, Pattie Maes
Published: 2026-09-01
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2609.00584v1

Does unrestricted AI access bypass the cognitive effort required for learning, or does it streamline knowledge acquisition? This paper reports on a study where we compare three designs for user-AI interaction in a learning context: (1) an unrestricted conversational bot like ChatGPT, (2) a pedagogically constrained bot that guides through hints without giving final answers, which we refer to as the Socratic mode; and (3) a non-conversational adaptive tutoring system that adjusts difficulty in real-time based on the user's cognitive engagement derived from the brain signals. Fifty study participants were tasked with learning about nuclear safety protocols, a domain chosen for its zero-prior knowledge baseline. The participants progressed through an instructional video, a pre-test, an AI-driven assessment phase, which varied in the three conditions, and an immediate post-test. The nature of the questions centered primarily on factual knowledge acquisition, but it still required participants to have a global understanding of the concepts in order to answer the questions correctly. A Muse headband was used to derive the cognitive engagement of all users in all conditions. The unrestricted chatbot produced higher learning gains (delta) than both constrained modes (p < .03, d > 0.80), while the adaptive condition generated significantly higher EEG engagement (p = .018). The cluster analysis of chatbot usage and discussion patterns by users showed that most participants in the unrestricted-mode adopted a direct answer-retrieval strategy, while participants in the Socratic-mode initially attempted to reason through the hints before progressively disengaging. Consequently, this also suggests that the success of the unrestricted AI is not an evidence of deeper learning, but rather a result of the immediate post-test evaluation after the training phase.

---

### Enoki: Efficient Multi-Level Hallucination Detection

Authors: Elisei Rykov, Timur Ionov, Nikolay Ivanov, Maksim Savkin, Maksim Makarenko, Alexander Panchenko, Vasily Konovalov, Julia Belikova
Published: 2026-09-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.00581v2

Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existing hallucination detectors usually operate at a single level: claim-level methods provide interpretable factual units, while span-level methods localize unsupported text. Bridging these views is costly, as LLM-heavy pipelines require multiple decomposition and verification calls, and modular systems need additional claim-to-span alignment. We propose Enoki, an Open Information Extraction framework for multi-level hallucination detection. Enoki extracts text-anchored relational facts, verifies them against evidence, and projects unsupported facts back to hallucinated spans. This shared representation enables claim-level verification and span-level localization without requiring separate alignment. Enoki supports LLM-based, encoder-based, and rule-based extraction regimes, balancing accuracy and inference cost through a common interface. Experiments show that Enoki remains competitive with strong claim-level systems while using fewer resources and achieves superior performance on fine-grained span- and entity-level localization. We also release EnokiQA, a dual-granularity dataset with aligned claim-level verification and span-level localization annotations.

---

### Predicting Program Exit Code with LLMs and Programming Language Semantics

Authors: Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa, Junyi Jessy Li, Milos Gligoric
Published: 2026-09-01
Categories: cs.PL, cs.AI, cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2609.00579v1

Large language models (LLMs) have shown proficiency in various software engineering tasks, such as code generation and translation. However, a key limitation in their performance may be their (lack of) understanding of programming-language semantics. Even when explicit semantics are given, it remains unclear whether LLMs apply those rules or lean on priors learned during pre-training instead. We study if LLMs lean on priors or given semantics with a novel task--Program Executability Prediction (PrEx)--that asks models to predict whether a program is semantically valid or invalid (and, if invalid, which formal rule it violates) given the program's syntax and operational semantics. Because PrEx requires both valid and invalid programs, we build a dataset with systematically generated invalid transformations derived from valid programs. We evaluate open-source coding LLMs under two semantic formalisms and two semantic shifts across Human-Written, LLM-Translated, and Fuzzer-Generated program splits. Our findings show that LLMs lean on pre-training priors rather than systematically applying the given rules, performing especially poorly on modified semantics and degrading further as program complexity increases. PrEx is available at https://github.com/EngineeringSoftware/prex.

---

### Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts

Authors: Rui Yang, Yang Hong, Yichao Xu, Zhengyu Liu, Ziyang Li, Yinzhi Cao
Published: 2026-09-01
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2609.00578v1

Large Language Models (LLMs) can solve complex problems, but their misuse in high-risk domains can lead to severe consequences. Model providers therefore restrict assistance for potentially harmful requests. Refusing all cybersecurity requests would therefore harm legitimate users. Providers need a mechanism to block malicious use without denying legitimate assistance to defenders. Existing cybersecurity-specific datasets evaluate this mechanism, but none considers the conversational context of a request. We introduce 3R-Bench (Refusal, Repetition, and Revision), a benchmark of 150 real-world cybersecurity requests augmented with two adversarial conversational settings, and evaluate eight LLMs on it. Prior assistant behavior strongly changes responses to an unchanged request: among 376 available pairs from a 400-pair panel, compliance rises from 62.0% after refused history to 85.1% after accepted history. The opposite pattern appears under dialogue decomposition. In comparison, compliance falls from 501/800 direct responses to 172/800 after dialogue; among 738 pairs returning model-authored text in both conditions, the decrease is 45.1 points. Failure feedback recovers only a small fraction of this loss.

---

### GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel Autoregressive Learning

Authors: Wenjian Wu, Zesheng Jia, Jiaying Tang, Benyuan Yang, Jin Wang
Published: 2026-09-01
Categories: cs.LG, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2609.00577v1

Multi-agent combinatorial optimization problems are notoriously challenging due to their NP-hard nature. Recent parallel autoregressive neural solvers improve inference efficiency by allowing agents to make decisions simultaneously, but their performance often degrades on large-scale instances. This is largely attributable to weak modeling of local geometric structures and the fact that conflicting task selections are handled only after action generation. To address these limitations, we propose GeoPAR, a geometry-guided parallel autoregressive reinforcement learning framework for scalable multi-agent combinatorial optimization. GeoPAR integrates three key components: (1) a projection-window sparse geometry mechanism that builds lightweight local candidate neighborhoods through multi-directional projections, (2) sparse edge-biased attention that injects these geometric relations into node representations, and (3) cache-guided conflict-aware assignment that reuses the geometric cache during decoding to suppress duplicate selections of exclusive tasks. Experiments on heterogeneous vehicle routing and open multi-depot pickup-and-delivery problems show that GeoPAR improves large-scale zero-shot generalization while substantially reducing rollout steps and maintaining efficient inference.

---

### Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random

Authors: Cris Huynh
Published: 2026-09-01
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2609.00576v1

Item-sensitivity, defined as whether a model's choice depends on the specific input rather than on its own output prior, is widely reported as evidence of task competence. We show this evidence is necessary but not sufficient using a forced-choice signalling task abstracted from the board game Deception: Murder in Hong Kong. In this environment, the reference points against which a coordinate should be judged (a fit-maximising strategy, a posterior-maximising strategy, and uniform random selection) are all computable in closed form. Across seven language models, two model families, a post-training ablation, and three independent scoring rules, every one of 21 model-by-rule cells is reliably item-sensitive. Yet 8 of those 21 cells are not statistically distinguishable from a chooser that ignores the item and selects at random, and 5 score worse than random at describing the target. Item-sensitivity and distance from random correlate at only r = 0.30. We call this consistency without alignment and argue it generalises to any evaluation that relies on item-sensitivity, permutation consistency, or self-consistency without an independent reference for the measured quantity. We further find that a literal-similarity baseline with no pragmatics outperforms most tested language models, that adding a pragmatic layer over two baseline similarity sources moves choosers toward random rather than toward the Bayesian reference, and that a standard labelled multiple-choice format carries no measurable content signal here. All results represent the model side of a pre-registered instrument; a matched human condition is designed and piloted but not yet collected.

---

### Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMs

Authors: Seungwoo Jung, Dohyeok Kwon, Seungmin Cha, Junseok Lee, Yeonho Yoo, Chuck Yoo, Gyeongsik Yang
Published: 2026-09-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.00575v2

Mixture-of-experts (MoE) architectures scale large language models efficiently, but they demand massive GPU memory. To cope with such demand, models are commonly compressed to reduce their memory footprint. Residual sparsification is a representative compression technique that decomposes each projection matrix of an expert into a shared base matrix and per-expert residual matrix, and then compresses the residuals. Existing sparsification methods compress each residual matrix independently by minimizing its compression error, thereby minimizing the error of each projection matrix. However, our analysis shows that this objective is misaligned with preserving model accuracy after compression. In an expert, the final output is produced through computations coupled across multiple projections and hidden representations. Therefore, even small errors in individual matrices can propagate through hidden representations and projection interactions, leading to large expert output errors and accuracy degradation. To address this misalignment, we propose PARSER, a new residual sparsification method that shifts the compression objective from minimizing isolated matrix errors to preserving the expert output error. PARSER achieves this by introducing output importance, which measures the actual contribution to the expert output error. Our experiments show that, compared with existing methods, PARSER narrows the accuracy gap to the uncompressed model by 1.41$\times$ on Qwen and 1.44$\times$ on DeepSeek, while achieving the same peak memory reduction. Our code is available at https://github.com/OSSS-KU/PARSER.

---

### A Mathematical Framework for Legacy, Governance, and Decision Integrity in Enterprise AI

Authors: Shorab Sarker
Published: 2026-09-01
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2609.00572v1

Enterprise artificial intelligence is increasingly embedded in decisions that must remain lawful, explainable, adaptable, and accountable despite personnel turnover, model replacement, regulatory change, and shifting organizational incentives. Existing governance frameworks provide important principles but do not by themselves supply a compact mathematical language for evaluating whether an institution can preserve sound judgment over time. This paper develops a design-science framework for institutional legacy: the durable capacity of a decision system to continue producing beneficial, lawful, explainable, and adaptable outcomes after its original designers have stepped away. The framework contributes: (i) a normalized Legacy Score based on a penalized geometric mean of knowledge retention, governance, human oversight, adaptability, feedback learning, and jurisdictional fidelity; (ii) Decision Confidence and Decision Risk models separating evidentiary confidence from consequence; (iii) authority-aware retrieval and calibrated abstention; (iv) Decision Memory for governed organizational learning; (v) Regulatory Change Velocity mapping change exposure to review intervals; and (vi) a federated regulatory knowledge-graph architecture preserving provenance and legal hierarchy. The paper also proposes eight AI Decision Integrity Rules, an evaluation protocol, and a reproducible computational demonstration. The demonstration combines a deterministic stress test with 200 Monte Carlo replications of 10,000 synthetic decisions each, illustrating Legacy Score non-compensation and comparing consequence- and authority-aware routing with a matched-coverage confidence-only baseline. The contribution remains conceptual rather than field-validated; the simulation tests internal behavior, not production performance, and all parameters require context-specific calibration.

---

### VoiceLongMemEval: Do Assistants Remember How You Sounded?

Authors: Ramit Pahwa, Parivesh Priye, Apoorva Beedu
Published: 2026-09-01
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2609.00570v2

With the growing scale of multi-agent architectures and large language models, deployed AI assistants are increasingly tasked with reasoning over long, continuous, multi-session conversation histories. Current benchmarks evaluate this dialogue history as information retrieval over long horizon, temporal reasoning, or knowledge updates, while crucially ignoring the fundamental dynamics of human-agent interaction, i.e. how they said it. To address this gap, we present VoiceLongMemEval (VLME) benchmark, where every answer depends on paralinguistic metadata (emotion labels, prosody descriptors, and voice events) attached to conversational turns, which is otherwise unrecoverable from the words alone. Every item passes a three-stage adversarial gate, ensuring that a strong language model fails when given only the transcript. Evaluating leading frontier and open-weight models reveals a pervasive affect gap; providing text-track paralinguistic metadata yields a 0.09 to 0.38 accuracy boost (0.61 to 0.69 when prompted with evidence hints), while standard ASR pipelines systematically discard this signal. Additionally, audio-native models successfully extract these cues directly from speech (0.354 to 0.412 vs. 0.325 blind). Code and dataset will be made available upon acceptance.

---

### WiseSpec: Requirements-Driven Agents for Code Generation

Authors: Zhao Tian
Published: 2026-09-01
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2609.00568v1

Code generation aims to automatically generate source code from task requirements and has attracted significant attention with the rapid advancement of large language models (LLMs). Despite remarkable progress, LLMs often struggle to generate correct code for complex software engineering tasks because task descriptions are frequently incomplete, ambiguous, or lack critical contextual information. Existing approaches primarily improve the capabilities of coding agents through more sophisticated tools, skills, and workflows, while largely overlooking the quality of the task requirements themselves. To address this limitation, we draw inspiration from software requirements engineering and propose WiseSpec, a novel requirements-driven agent framework for repository-level code generation. WiseSpec automatically constructs structured and information-rich requirements, assesses their quality through execution-based evaluation, and iteratively refines them to better guide code generation. Experimental results show that WiseSpec consistently outperforms all baselines, achieving an average improvement of 13.17% in %Resolved.

---

### EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target Selection

Authors: Guanzhong Sun, Junyi Ma, Yuxuan Wu, Wei Tang, Yanzi Miao
Published: 2026-09-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.00566v3

We propose EEG-VID, a task-guided latent predictive pretraining framework for EEG decoding under session and subject shifts. EEG-VID predicts future latent EEG states from recent history using an exponential-moving-average target encoder and weak task guidance, followed by supervised fine-tuning. Across VIG-48 and BCI Competition IV-2a/IV-2b, Stage 1 improves mean accuracy in 41 of 42 matched backbone-dataset-protocol comparisons, including all 12 leave-one-subject-out settings, with a maximum gain of 16.22 percentage points. On the 48-region cross-day VIG-48 task, EEG-VID achieves 6.52% Top-1 and 30.50% Top-5 accuracy. In a separate six-participant offline robot-scene study, candidate-constrained target selection reaches 40.24% versus a 25% chance level after subject-specific calibration. These results support task-guided latent prediction as a transferable pretraining strategy for EEG decoding and scene-constrained assistive target selection.

---

### Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs

Authors: Jingshen Zhang, Shaoyang Xu, Wenxuan Zhang
Published: 2026-09-01
Categories: cs.SI, cs.CL
arXiv: https://arxiv.org/abs/2609.00565v1

Cultural fine-tuning has become the de facto paradigm for building culture-aware large language models (LLMs), yet existing optimization exclusively for alignment scores provides an incomplete portrait of cultural fidelity by systematically obscuring inherent cultural diversity. This unidimensional evaluation lens prompts a fundamental question: do models genuinely perceive distinct cultural nuances, or do they merely memorize dominant cultural values? To address this, we propose a synergistic evaluation framework that jointly formalizes cultural alignment and diversity. Through extensive benchmarking of six mainstream LLMs on the World Values Survey, this framework uncovers a systematic and critical trade-off: the pursuit of cultural alignment consistently incurs an acute expense of diversity, leading to severe "cultural flattening." Investigating this behavioral shift, we demonstrate that these superficial alignment gains stem from models artificially anchoring to dominant majorities, converging onto a monolithic response pattern that wipes out the heterogeneous distributions inherent to human groups. Crucially, our mechanistic analysis suggests that this diversity collapse is not merely a behavioral anomaly but more likely a structural consequence of the low-rank bias inherent in neural network optimization. Therefore, our findings expose the limitations of current post-training paradigms and call for a shift toward alignment objectives that preserve cross-cultural pluralism.

---

### Potential-Guided Particle Steering for Negation-Constrained Dexterous Grasping

Authors: Geonho Kim, SooGon Kim, Jongmin Lee
Published: 2026-09-01
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2609.00555v1

Language-driven dexterous grasp models, such as DextER, perform well when instructions specify where to grasp, but we find they fail systematically when an instruction also specifies where not to grasp (e.g., "grasp the handle but avoid the body"). Existing training corpora, DexGYSNet among them, contain virtually no avoidance instructions, and collecting examples for every possible constraint is impractical. Moreover, because every part mentioned during training denotes a contact target, models may interpret a forbidden part as another region to grasp rather than one to avoid. We therefore introduce an inference-time framework for negation-constrained dexterous grasping that requires no negation-specific training examples. Combining Sequential Monte Carlo with classifier-free guidance, our method guides sampling toward the instructed part while pruning candidates headed for the forbidden region, without any negation examples during training. A frozen 3D part-grounding model localizes the forbidden region from the language instruction. To evaluate this setting, we construct NegGrasp, a benchmark of paired positive/negative instructions with constraint-aware metrics that credit a grasp only if it both accomplishes the task and respects the stated constraint. On NegGrasp, our method reduces the violation rate of the strongest baseline from 57.9% to 17.2% while improving both constraint-aware and physical success.

---

### Manifold-Aware General Coded Computing for Straggler-Resilient Distributed Computing

Authors: Parsa Moradi, Mohammad Ali Maddah-Ali
Published: 2026-09-01
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2609.00552v1

Existing coded-computing designs do not explicitly exploit the intrinsic structure of the input data. In communication systems, statistical structure and redundancy are often removed through source coding (or compression) before channel coding is applied. This principle, however, does not transfer directly to coded computation. In many computational tasks, particularly in machine learning, the structure of the data is precisely what the computation seeks to exploit to infer outputs or learn meaningful patterns. Consequently, coded-computing schemes should preserve and leverage this structure in their code design, rather than ignoring or eliminating it through source coding. This observation motivates a different perspective on code construction. In many channel-coding schemes, such as Reed-Solomon codes, coded symbols are generated by evaluating a low-dimensional algebraic representation at selected points. In contrast, many high-dimensional datasets naturally concentrate near low-dimensional manifolds. In this paper, we exploit this intrinsic geometry by designing coded samples that follow the natural manifold of the data, rather than imposing an artificial low-dimensional structure unrelated to the data distribution. Inspired by graph-based manifold learning, we propose a manifold-aware encoding strategy for general coded computing (GCC). Experiments on neural network inference and high-dimensional polynomial evaluation demonstrate that the proposed strategy consistently and significantly reduces the mean squared recovery error under straggling compared with standard GCC.

---

### EM^2Mem: Event-Centric Multimodal Memory for Large Language Models

Authors: Yijun Chen, Yaqi Zheng, Yanya Li, Boyi Xiao, Buqiang Xu, Shuofei Qiao, Jizhan Fang, Xinle Deng, Yunzhi Yao, Xuehai Wang, Liuxin Zhang, Hui Li et al.
Published: 2026-09-01
Categories: cs.CL, cs.AI, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2609.00551v1

Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as isolated fragments. Although searchable, such fragments are not generation-ready: language models must reconstruct cross-modal and temporal alignments at inference time, when context is limited and attribution is difficult. We propose EM^2Mem, an event-centric multimodal memory framework that binds heterogeneous evidence to event anchors during memory construction. Each event-indexed memory cell aligns multimodal records, temporal context, graph-linked relations, semantic facts, and provenance, enabling compact evidence readout over grounded multimodal events rather than modality-specific fragments. Across three long-video QA benchmarks, EM^2Mem improves average accuracy over the strongest memory baseline by 2.0, 2.4, and 3.7 points, improves strict event-level Top-5 evidence recall by 7.0 points, and reduces per-query latency by 4.67 times and total inference tokens by 63.66% (The code will be integrated into https://github.com/zjunlp/LightMem).

---

### Same Semantics, Different Outcome: On the Modality Robustness of Multimodal LLMs under Knowledge Conflict

Authors: Jungyeon Lee, Yejin Yoon, Taeuk Kim
Published: 2026-09-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.00550v1

Multimodal large language models (MLLMs) are increasingly provided with contextual evidence in heterogeneous forms: as a text passage, as a rendered image of the same passage, or as both together. However, it remains unclear how consistently these surface forms are processed, especially when the evidence conflicts with the model's parametric knowledge. We study modality robustness under knowledge conflict across 13 MLLMs and two datasets, and find them far from robust. (1) Contrary to common belief, models favor a context that contradicts parametric knowledge more readily in image form than in text form; (2) when a contradicting text and image are presented together, the preferred modality is essentially arbitrary, varying with input order, model, and dataset. We further demonstrate that this instability has practical consequences: it degrades performance in multimodal RAG and can be exploited by adversarial attacks. To alleviate this brittleness, we examine several simple techniques---prompting, steering, supervised fine-tuning (SFT), and direct preference optimization; the majority prove ineffective, whereas SFT achieves moderate success. We therefore call for greater awareness of this inconsistency and argue that it is fundamental, demanding attention at multiple training stages.

---

### Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM Agents

Authors: Seonghyeon Cho, Chanjun Park
Published: 2026-09-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.00549v1

Large Language Model (LLM) agents increasingly rely on external skills, yet standard evaluations obscure whether retrieving these skills actually helps. Aggregate metrics often compare retrieved versus non-retrieved tasks, introducing severe selection bias and failing to isolate the true effect of skill use. To measure this actual-use capability-which we formalize as Skill Following (SF)-we introduce the Retrieval-Invoked Actual-Use Effect (RAE). RAE computes the same-task outcome difference between matched skill-enabled and skill-disabled executions, conditioned exclusively on tasks where the agent actively retrieved a skill. Evaluating 17 LLMs across coding and mathematical domains, we uncover a stark evaluation paradox: models frequently show positive aggregate retrieval lift but negative RAE. On MBPP+, multiple models that appear to benefit system-wide actually harm their own performance on the exact tasks where retrieval occurred. These findings demonstrate that aggregate averages can create a misleading illusion of tool-use proficiency, whereas RAE directly measures whether the retrieval-to-answer pipeline genuinely rescues more outcomes than it harms.

---

### Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Servers

Authors: Zhenyu Zhao, Roy Zhao
Published: 2026-09-01
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2609.00546v2

Long-lived AI agents may replace their models, orchestration harnesses, interaction surfaces and hosts while retaining identity, memory and executable body lineage. We present a runtime-independent architecture that separates a continuity-bearing substrate $P_t=(I_t,M_t,B_t)$ from replaceable execution and interaction bindings. Six continuity invariants and a quiesce--checkpoint--validate--bind--rehydrate--resume protocol govern state preservation, capability changes and continuation authority. Enoch implements the design through a reusable software body, private installed state, provider contracts and fenced migration. We report complementary evidence from frozen implementation snapshots and three kinds of live study. An operational case retains an established instance's identity, nonempty memory, body revision and historical task IDs across host, joint Codex-to-Claude model/harness, and chat-surface substitutions. A separate cross-host task resumes from a verified artifact checkpoint. A supervised Codex--Muse--Codex study completes five ordinary round trips and five matched same-runtime controls on their first attempts after a separate qualification run. A planned worker interruption recovers through the native task API with the checkpoint preserved, a stale reply rejected and one task completion recorded. These results support mechanical continuity for the tested deployments and bounded workflows. They do not establish behavioral equivalence, arbitrary-task portability, general exactly-once external effects or unattended reliability.

---

### GenONet: A Generative operator Network for High-Resolution Precipitation Nowcasting

Authors: Mohammad Kian Golkar, Luciano Alves de Oliveira, Mohammad Khanjani
Published: 2026-09-01
Categories: cs.LG, physics.ao-ph
arXiv: https://arxiv.org/abs/2609.00544v1

High-resolution precipitation nowcasting is critical for reducing the impacts of severe weather but remains difficult because of rapid storm evolution. Deep learning models have shown great promise for this task, but their predictive skill often deteriorates over longer forecast horizons. This leads to increasingly blurry forecasts that fail to capture the complex, non-linear evolution of storm systems. In order to address these limitations, we introduce Spatio-Temporal U-DeepONet (GenONet), a novel architecture for long-range precipitation forecasting up to 3 hours, specifically designed to produce sharp and physically consistent results. GenONet's architecture pioneers the use of a Deep Operator Network (DeepONet) as a generator within a Generative Adversarial Network (GAN) framework for this task. The DeepONet learns the continuous-time dynamics of precipitation, ensuring stability over long forecast horizons. Adversial training against a spatio-temporal discriminator compels the model to produce sharp, coherent forecasts, while a physics-informed loss regularizer, derived from the Moisture Conservation Equation, improves physical plausibility in our ablation setting. Quantitative evaluations show that our model achieves consistently higher scores on most of the metrics, especially for highintensity events and at longer lead times. Qualitatively, GenONet produces structurally coherent forecasts that maintain their integrity, whereas baseline models degrade into indistinct patterns. Finally, an ablation study confirms the benefit of this physics-informed loss, highlighting the strength of combining operator learning with adversarial training.

---

### Feedback-Assisted Trust Propagation over Document Relation Graphs for Retrieval-Augmented Generation

Authors: Zhuoheng Li, Ying Chen
Published: 2026-09-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.00543v1

Retrieval-augmented generation (RAG) systems rely on external corpora that may contain outdated, contradictory, noisy, or unreliable documents, introducing reliability risks. Prior work has leveraged document relations to improve the answer reliability of RAG. To propagate reliability signals beyond directly compared document pairs, we propose TrustPropRAG, which structures document relations as a graph and estimates document reliability through multi-hop propagation across the graph. TrustPropRAG anchors this propagation with a limited set of human feedback on document reliability, extending these costly-to-collect feedback-based reliability signals across the whole corpus. Specifically, based on the constructed document relation graph, TrustPropRAG estimates a trust score for each document by formulating and solving an optimization problem that jointly captures pairwise document relations and user feedback. These scores are then used to improve the selection of reliable documents and support trust-aware answer generation. Evaluation results show that TrustPropRAG improves both retrieval quality and exact match over baselines, and remains robust under sparse and noisy feedback.

---

### DeSyR: A Decoupled Symbolic Recovery Framework with PINN-Guided Structure Search and Physics-Informed Coefficient Refinement

Authors: Pancheng Niu, Jun Guo, Qiaolin He, Jingcai Guo, Yanchao Shi
Published: 2026-09-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.00530v1

Recovering compact explicit solutions from neural approximations is challenging when imperfect teacher data guide symbolic topology search and coefficient estimation. We present DeSyR, a decoupled symbolic recovery framework for differential equations. A physics-informed neural network guides repeated searches to construct candidate topologies with provisional constants. Once a topology is fixed, its coefficients are refined solely from the governing equation and prescribed constraints, followed by gated selection and verification. For linear fixed-topology parameterizations, we characterize teacher-error inheritance and show that finite-weight mixed data--physics fitting retains an $O(β^{-1})$ teacher-dependent contribution when the teacher error projects onto the model space. Under well-posedness, representability, zero-residual attainment, and discrete determinacy, physics-only refinement conditionally recovers exact coefficients; for nonlinear parameterizations, the corresponding guarantees are local. DeSyR is evaluated on 15 differential-equation problems across 18 configurations covering high-order, space--time, multidimensional, nonlinear, and coupled systems. A candidate-level audit yields a 99.23% convergence rate among free-parameter refits, while every selected refinement involving free coefficients converges. Configuration-level median refined relative $L_2$ errors are $2.31\times10^{-14}$ or lower. In same-topology comparisons, refinement reduces error by eight to fourteen orders of magnitude. These results show that an approximate neural teacher can guide topology discovery without imposing its error scale on final recovered coefficients, provided a target-capable topology is retained and physics-only refinement converges.

---

### Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials

Authors: Pingbing Ming, Han Wang
Published: 2026-09-01
Categories: cs.LG, math-ph, physics.chem-ph, physics.comp-ph
arXiv: https://arxiv.org/abs/2609.00528v2

We prove that the Hypergraph Neural Network, an invariant architecture with 3-body message passing, is a universal approximator for potential energy surfaces. Our main contribution is a multi-layer completeness theory. We show that $L$ layers of message passing on sparse, cutoff-based graphs achieve the same representational power as having access to the full $L$-hop neighborhood, provided the configurations are generic, satisfy an overlap condition and a connectivity condition. This provides the first rigorous justification for the common practice of using multi-layer message passing with a per-layer cutoff smaller than the physical interaction range, the setting used by virtually all practical graph neural network based machine-learned interatomic potentials. As immediate consequences, we show that both DPA3 and CHGNet architectures inherit universal approximation.

---

### GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing

Authors: Lingxiao Li, Max Whitton, Ledell Wu, Boqing Gong
Published: 2026-09-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.00525v1

Modern image generation and editing systems can produce photorealistic, prompt-aligned images, but still often render familiar objects at implausible relative sizes. To measure this failure mode, we introduce GenScale, a benchmark and evaluation protocol for real-world relative object scale in image generation and editing. GenScale contains 900 image-level entries and 1,643 pairwise anchor-target scale relations across common-object generation, human-product generation with metric dimensions, and scale correction from failed generations. We further design a human-calibrated ordinal judge for scalable pairwise scale evaluation. Last but not the least, we introduce Rescale, a model-agnostic post-processing agent for localized scale correction without modifying the source generator. Experiments reveal that state-of-the-art image generators and editors cannot reliably observe relative scale yet, while Rescale consistently improves scale plausibility across generated and edited images. Together, GenScale establishes relative object scale as a distinct, measurable, and actionable capability for image generation systems.

---

### Are We There Yet? Assessing Computer-Use Agents for Blind Users' Accessible Interaction with Desktop Applications

Authors: Satwik Ram Kodandaram, Monalika Padma Reddy, Xiaojun Bi, Jiawei Zhou, I. V. Ramakrishnan, Vikas Ashok
Published: 2026-09-01
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2609.00524v1

Computer-use agents are emerging as a paradigm for agentic human-AI interaction, combining language reasoning with multi-modal interface grounding to operate GUIs. Yet their effectiveness for blind screen-reader users in real-world desktop workflows remains unclear. We present a three-week diary study with 8 blind users using OLLA, a screen-reader-accessible CUA prototype, collecting 1,258 commands across 12 applications with screenshots, UI trees, model responses, and action traces. We evaluate GPT-5 during deployment and re-execute the same commands with four additional models. GPT-5 achieved the highest success rate at 52.5%. Trace analysis reveals grounding, planning, constraint-tracking, and termination failures, while interviews reveal beyond-automation needs.

---

### Soft-Argmax for the Projective Plane via the Veronese Embedding

Authors: Benjamin El-Zein, Dominik Eckert, Paul Zech, Christopher Syben, Bernhard Geiger, Steffen Kappler, Sebastian Stober
Published: 2026-09-01
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2609.00521v1

From horizon detection to fibre structures in X-ray imaging, many vision tasks recover lines via peak detection in Hough space $H=S^1\times\mathbb{R}$, the domain of orientation-offset pairs $(θ,ρ)$. Differentiable pipelines extract coordinates via \emph{soft-argmax}, a probability-weighted average that is only meaningful in a globally linear space. However, $(θ,ρ)$ and $(θ+π,-ρ)$ describe the same undirected line, so $H$ double-covers the space of undirected lines $H/\mathbb{Z}_2$: a Möbius strip, obtained by identifying each pair under $\mathbb{Z}_2$ action. Soft-argmax operates on the cover $H$, but since $H/\mathbb{Z}_2$ admits no linear structure, it tears geometrically adjacent lines apart. Thus we need a $\mathbb{Z}_2$-invariant embedding of lines into a linear space, on which soft-argmax is well-defined. We achieve this by parametrising lines via unit-norm homogeneous vectors $\ell=(1+ρ^2)^{-1/2}(\cosθ,\sinθ,-ρ)^{\top}\in\mathbb{R}^3$ and applying the Veronese map $v_2(\ell)=\ell\ell^{\top}$ that satisfies $v_2(\ell)=v_2(-\ell)$. This descends continuously to an embedding of the quotient $H/\mathbb{Z}_2$ into the linear space $\mathrm{Sym}^2(\mathbb{R}^3)$, where the antipodal ambiguity vanishes. Line extraction becomes a barycentre in $\mathrm{Sym}^2(\mathbb{R}^3)$, projected back via its leading eigenvector. We validate our \emph{Veronese soft-argmax} in a Hough transform-based network across all resolvable lines, confirming uniform and seam-free recovery. We further derive that the $L_2$-loss on isometrically weighted Veronese embeddings equals the squared chordal distance between lines in projective space, enabling a geometrically precise training objective.

---

### The Safeguard Worked. Is the LLM System Safer?

Authors: Pingyu Wu, Weiming Zhang, Nenghai Yu
Published: 2026-09-01
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.00519v1

Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control performed on the requests it was tested on. A deployment has to answer a different question: how much help with harmful tasks the service still gives an attacker who keeps adapting or finds another way in. We determine what each reported result implies for that question, allowing results from different safeguard families to be compared under one deployment criterion. The evidence requirements are strongly asymmetric. One attack that obtains harmful help from the deployed service suffices to establish that such help remains, and such attacks appear repeatedly in the coded record. Establishing that little remains cannot follow from the safeguard's own numbers alone; it also requires evidence about what the surrounding system still allows after the safeguard performs its local function. Such evidence is supported or derived in only a small minority of the depth-coded claims, and one such claim bounds its scoped residual. A better local score is therefore not, by itself, a stronger claim about the deployment. Safeguard research cannot stop at raising local scores; a gain has to be judged by whether it makes a deployed system any safer.

---

### Learning Task-Specific Antibody Representations via Function-Aware Masking

Authors: Ayan Goel, Thomas A. Walton, Amirali Aghazadeh
Published: 2026-09-01
Categories: cs.LG, q-bio.BM
arXiv: https://arxiv.org/abs/2609.00518v1

Antibody-specific language models pretrained via masked language modeling (MLM) learn representations that are critical for downstream sequence design and property prediction tasks. Yet, the corruption process itself is rarely leveraged as a source of inductive bias during pretraining. While preferentially masking complementarity-determining regions (CDRs) improves binding-related predictions, antibodies possess diverse biological priors over a variety of functions. Herein, we introduce function-aware masking, a family of pretraining algorithms that align mask placement with specific functional priors (e.g., from IMGT annotations or structure predictions) to shape the learned representation space. We show that these specialist masking strategies significantly improve performance on their respective objectives, yielding up to a 14% gain on structure-related tasks and up to a 5.9x improvement on CDR-related tasks. To further improve performance across multiple functional axes, we develop hybrid masking strategies that integrate multiple priors, balancing reconstruction over binding, structural, and biophysical objectives. Our results demonstrate that informed mask placement provides a parameter-free mechanism for imposing functional inductive biases in antibody language model training.

---

### The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space

Authors: Jacob Brinton, Jannik Brinkmann, Mark Crovella, Aaron Mueller
Published: 2026-09-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2609.00515v1

Large language models (LLMs) have recently demonstrated improved machine translation performance over strong supervised baselines. This raises questions as to what mechanisms underlie how LLMs perform machine translation between languages. Motivated by recent interpretability findings--namely, that LLMs use massively multilingual latent feature representations to perform language modeling--we propose the interlingua hypothesis. The hypothesis holds that language models translate by reading a source sentence into a latent feature space, and generate a target sentence by reading from the latent feature space. We show three lines of evidence in support of this hypothesis: (1) variance in BLEU across language pairs is largely predictable from language-specific competences with no language pair-specific interaction terms; (2) many model components are causally influential in both monolingual tasks and translation tasks; and (3) fine-tuning on monolingual data recovers a large proportion of translation improvements relative to fine-tuning on aligned documents. Together, these provide convergent evidence in support of the interlingua hypothesis, and suggest new ways of understanding and improving how LLMs can be leveraged to perform translation tasks.

---

### ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation

Authors: Siyuan Zhang, Hanchen Wang, Dong Wen, Ying Zhang, Wenjie Zhang
Published: 2026-09-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.00513v1

Retrieval-Augmented Generation (RAG) mitigates large language models (LLMs) hallucinations, yet conventional dense retrieval struggles with the complex reasoning paths of multi-hop question answering (QA). Graph-based RAG captures multi-step relationships but suffers from severe semantic drift and high online latency due to noisy global graph traversals. Thus, we propose ISO-RAG (ISOperimetric Retrieval-Augmented Generation), a geometry-aware RAG framework. By projecting the underlying knowledge graph into a hyperbolic Poincare ball to precompute node-wise isoperimetric profiles, ISO-RAG prunes spurious edges during retrieval, restricting the search space to a strictly localized subgraph. This topological purification regulates Personalized PageRank (PPR) diffusion driving the retrieval process, ensuring exact and low-latency convergence. Experiments on multi-hop QA benchmarks demonstrate that ISO-RAG outperforms state-of-the-art baselines by average absolute gains of 10.0% in retrieval recall and 4.3% in downstream exact match, achieving a superior accuracy-efficiency trade-off by fundamentally eliminating the latency bottleneck of global traversals. Our source code is available at https://github.com/ZaiizaiZHANG/ISO-RAG.

---

### When the Algorithm Becomes the Brand Crisis: A Sociotechnical Theory of Distributed Responsibility and Accountable Transparency

Authors: Mohammad Saleh Torkestani, Taha Mansouri
Published: 2026-09-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.00510v1

Artificial intelligence systems increasingly enact market-facing promises through chatbots, recommendation systems, automated decisions, and generative interfaces. Their failures, misuse, and misrepresentation raise a question that conventional brand-crisis models do not fully specify: how do stakeholders assign responsibility when technical causation, customer-facing control, and governance duties are distributed across an AI system, developer, deployer, vendor, and user? This conceptual paper develops a sociotechnical process theory from a structured, federated scoping synthesis of verified academic and primary sources. It distinguishes an AI/algorithmic incident from an AI-related organisational crisis and, in turn, from an AI-related organisational scandal. The framework proposes that incident configuration shapes actor-specific attribution; attribution informs capability, integrity, fairness, and relationship appraisals; and public moralisation may, but need not, escalate an incident into scandal. The theory offers a reconciliation of findings that algorithm involvement can buffer negative brand reactions in some settings while robot and chatbot failures can redirect responsibility to an associated firm in others. It introduces accountable transparency as a proposed response configuration that combines timely notice, an intelligible account, role-responsibility acknowledgement, remedy, evidence of correction, and recourse. The evidence supports conditional, proximal inferences about blame, trust, satisfaction, firm evaluation, and communication credibility more strongly than claims about durable reputation, brand equity, or market performance.

---

### CoVer: Conflict-Aware Claim Verification

Authors: Shuning Zhang, Dai Shi, Bohao Chu, Hui Wang, Yuwei Chuai, Yifan Wang, Jingruo Chen, Simin Li, Xin Yi, Hewu Li
Published: 2026-09-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.00508v1

Social media fact-checking has long been challenged by evidence-level and aggregation-level conflicts, where erroneous evidence mimics authoritative news sources. To capture this challenge and support conflict verification tasks, we present ContraNote, a large-scale real-world dataset curated from X's Community Notes system. It includes 33,686 posts for evaluating evidence-level conflict resolution, and 54,474 instances for evaluating aggregation-level prioritization. Additionally, we propose CoVer, a factual adjudication framework with three-stage pipelines: evidence schema normalization, factual consensus and support verification. This prioritizes evidence over noise to prevent it from compromising the final verdict. Technical evaluations show that CoVer achieves strong performance compared with state-of-the-art baselines across ContraNote (86.0% Acc., 68.0% mac. F1, 64.5 bal. Acc. on Conflict; and 88.5% Acc., 88.5 mac. F1 and 89.2 bal. Acc. on Prioritization), CONFACT-HumC (88.4% Acc.) and CONFACT-ModC (89.4% Acc.).

---

### VATO: A Vortex-Force-Aware Transformer Operator for Unsteady Separated Aerofoil Flows

Authors: Xingxin Yang, Zhan Zhang, Yichen Li, Juan Li
Published: 2026-09-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.00507v1

Accurate prediction of unsteady separated flows is challenging because the aerodynamic loads depend on nonlinear separation and vortex-shedding dynamics. Although high-fidelity CFD resolves these mechanisms, its cost limits repeated use in design and control. Standard field-level surrogate training, however, does not distinguish the flow regions that contribute most strongly to the aerodynamic loads. We introduce VATO (Vortex-Force-Aware Transformer Operator), which couples the Vortex Force Map (VFM) method to a geometry-aware neural operator through two complementary mechanisms. VATO-S adds training-only supervision of the local VFM force-contribution field, with no increase in model size or inference cost. VATO-A uses VFM contribution and sensitivity fields to prioritise force-relevant source locations for residual cross attention. The methods are evaluated on unsteady CFD data for double-edged-plate aerofoils over 54 trajectories from nine geometries. Over lead times of 1-20~ms, VATO-S reduces velocity, pressure, and vorticity errors by 10.4\%, 1.0\%, and 15.6\%, respectively, while VATO-A achieves reductions of 15.8\%, 7.5\%, and 31.2\%. VATO-S gives the lowest VFM-derived drag error, whereas VATO-A gives the lowest pressure-derived lift and drag errors. Over lead times extending 50\% beyond the training range, VATO-A retains a 26.9\% reduction in vorticity error and larger improvements in all four force readouts, despite reduced gains in velocity and pressure. These results show that force-aware operator learning can improve both flow-field prediction and aerodynamic functional accuracy in unsteady separated flows.

---

### RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces

Authors: Nikhil Wani
Published: 2026-09-01
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2609.00506v1

Large language models are powerful, but their interfaces often devolve into a type $\rightarrow$ read $\rightarrow$ retype loop, creating conversational AI fatigue, cognitive load, and eventual task abandonment. To mitigate this, we present RecalibrateGPT, a system introducing five cross-turn operators (Anchor, Replay, Delta, Scope, and Steer) that each target a distinct fatigue type, recalibrating LLM responses through a structured panel by acting on the full conversation history with a single click. Users invoke these operators through the AssistiveButton in one of three operator palette layouts: Vertical, Arc, or Tablet. We conducted two pilot studies with the same 12 advanced LLM users. An initial formative qualitative study identifies a taxonomy of four fatigue types (retyping, scanning, decision paralysis, and context drift) and derives two design objectives for RecalibrateGPT. A follow-up quantitative evaluation finds it reduces perceived cognitive workload by half (NASA-TLX = 2.7) at high perceived usability (SUS = 86.5), suggesting AI fatigue is not just a model-quality issue but an interaction-flow cost that interfaces can remove.

---

### ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits

Authors: Sethuraman T, Savya Khosla, Onkar Kishor Susladkar, Aditi Tiwari, Seoung Wug Oh, Kushal Kafle, Joon-Young Lee, Derek Hoiem, Simon Jenni
Published: 2026-09-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.00505v1

Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal blindness, the inability to perceive fundamental cues like order, direction, and motion dynamics. Standard datasets mask this limitation by enabling models to exploit static spatial shortcuts. To systematically evaluate this, we introduce XTE-Bench, a diagnostic probe revealing that even large-scale video-language models struggle with basic temporal reasoning, indicating that parameter scaling alone is insufficient to resolve this flaw. To address this, we propose Cross-Modal Temporal Edits (XTE), a self-supervised framework that injects precise temporal supervision. By performing synchronized video-text transformations, XTE generates hard temporal negatives without manual annotation. We instantiate this with ViTAL-X, a lightweight model that equips frozen image-text backbones with temporal awareness while preserving their foundational spatial knowledge. Across six temporal benchmarks, ViTAL-X achieves state-of-the-art performance. Utilizing only 0.4B parameters and 1M training clips, ViTAL-X outperforms 7B-parameter models and surpasses baselines trained on 600x more data. These results demonstrate that targeted, high-quality temporal alignment provides a highly efficient alternative to pure scaling.

---

### Independent Reinforcement Learning in Discounted Markov Games

Authors: Asrin Efe Yorulmaz, Ugur Aydin, Tamer Basar
Published: 2026-09-01
Categories: cs.GT, cs.AI, cs.LG, eess.SY, math.OC
arXiv: https://arxiv.org/abs/2609.00504v1

In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming ``$\mathsf{ETH}$ for $\mathsf{PPAD}$", we show that, for every fixed discount factor, there is no polynomial-time algorithm for computing inverse-polynomially accurate coarse correlated equilibria in discounted general-sum Markov games when players learn independently in decentralized settings. Complementing this hardness result, we provide what appears to be the first \emph{radically uncoupled} algorithm with sub-exponential convergence guarantees to coarse correlated equilibria in discounted general-sum Markov games without imposing any structural restrictions on the game. Our algorithm is a \emph{layered} variant of optimistic mirror descent with an increasing step-size schedule tailored to the multi-agent setting. Finally, we develop both full-feedback and partial feedback versions of the aforementioned algorithm and establish sub-exponential convergence guarantees for each case.

---

### Wave Function Backpropagation with Explicit Temporal-Interval Dynamics

Authors: Byunggu Yu, Justin Kim
Published: 2026-09-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.00503v1

Conventional neural networks learn predominantly through affine transformations followed by nonlinear activations, while elapsed time is often treated as an auxiliary feature or assumed to be uniformly sampled. This paper introduces Wave Function Backpropagation (WFB), a wave-parameterized learning formulation in which neural responses are represented by learnable amplitude, wavenumber, angular frequency, and phase. The formulation associates an observed state with its temporal interval Delta t through the phase of a differentiable spatiotemporal wave. We derive standard WFB gradients and a spatial-curvature correction based on the Laplacian of the wave response. WFB is instantiated in a deliberately feed-forward trajectory predictor to provide a controlled proof of concept; sequence learning is outside the scope of the present evaluation. With motion features, STD-WFB using real intervals reduces average displacement error (ADE) by 20.4% relative to the original FFN baseline. In a new position-only evaluation that removes temporal leakage through precomputed velocity and acceleration, real-interval WFB reduces ADE by 10.4% relative to the original FFN and remains competitive with parameter-matched ReLU controls, obtaining 2.1% lower mean ADE than the matched FFN with explicit Delta t. Shuffled-interval WFB attains the lowest mean ADE, indicating that the present evidence supports the effectiveness of the wave representation but does not attribute the gain to interval alignment. These results establish WFB as a viable structured feed-forward learning formulation and define a clear basis for subsequent architectural studies.

---