Artificial Intelligence
PsychJail: Exploring Psychological Jailbreaks via Multi-Turn Persuasion of LLM Policies
Zeyu Feng, Qingyu Wu, Yuzhe Luo et al. (+1 more)
Large
language models (LLMs) are increasingly deployed in education, healthcare, policy advising, and other interactive settings, where users engage them as sustained social interlocutors rather than one-shot query engines. This shift makes jailbreaks a growing safety threat, yet most research emphasizes single-turn
prompt optimization or iterative attack refinement, leaving psychologically grounded multi-turn vulnerabilities underexplored. We present PsychJail, a psychology-guided framework for red teaming aligned LLMs through theory-grounded, multi-turn persuasion. PsychJail maps established social-psychological persuasion techniques into a tactic-conditioned attack policy. It factorizes each attacker action into a Change-of-Meaning analysis, tactic selection, and victim-visible message, operationalizing the Persuasion Knowledge Model (PKM). The policy is refined with trajectory-level reinforcement learning using a PKM-gated reward that credits early jailbreak success only when every turn contains a well-formed Change-of-Meaning analysis. Across four aligned victim models, PsychJail achieves the highest average attack success rate (87.3%) and outperforms strong single-turn and multi-turn baselines on every model. We also measure susceptibility at the action that breaks each victim, revealing four distinct model-level fingerprints that identify which persuasion levers affect each model and how broadly. These fingerprints help explain cross-model transfer asymmetry. We interpret them as four candidate psychological profiles-rationalist, credibility-driven, narrative-monoculture, and broadly persuadable-while treating this interpretation as a
conjecture requiring future validation. Our findings establish psychological jailbreaks as a distinct red-teaming frontier for increasingly interactive LLMs.
Read the full abstract ▾
All authors Zeyu Feng, Qingyu Wu, Yuzhe Luo, Hua Cheng
Artificial Intelligence · Cross-listed from cs.CL
Beyond Surface Cues: Disentangling Sociocultural Signals in Multilingual LLMs
Yuanjun Feng, Tanzhou Liu, Stefan Feuerriegel et al. (+1 more)
Multilingual LLM outputs can vary across sociocultural contexts. However, evidence of cultural grounding can be misleading: identity labels may be inferred from explicit or indirect textual cues, while names and wording can reveal the source
language. Treating all these signals as evidence of cultural grounding may obscure potential biases. We present a human-validated, multi-
agent audit that separates three questions: whether outputs reproduce social biases, whether identity groups are represented differently, and whether outputs reflect cross-cultural patterns. The study analyzes 89,253 outputs from 12 LLMs in English, French, and Chinese, spanning 18 occupations and three task conditions. We find that bias representation varies systematically across
languages and tasks. Removing direct identity cues sharply reduces identity-label prediction in English and Chinese, but has a much smaller effect in French. Across all
language-genre settings, the cultural context associated with the source
language receives the highest average relevance score, with moderate agreement between automated and human ratings. However, the ability to identify the source
language drops substantially after translation and again after masking names. Without these controls,
multilingual audits may mistake surface cues for cultural understanding, leading to misleading conclusions about cross-cultural variation and bias. Our audit offers a practical framework for separating such shortcuts from more meaningful cross-cultural patterns.
Read the full abstract ▾
All authors Yuanjun Feng, Tanzhou Liu, Stefan Feuerriegel, Yash Raj Shrestha
Artificial Intelligence · Cross-listed from cs.CL
Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality
Xunlei Chen, Qirui Ye, Yuang Li et al. (+5 more)
Large
language models (LLMs) require effective unlearning to address
privacy regulations and safety concerns. However, achieving precise forgetting without compromising general utility remains challenging. Existing sequence- and
token-level methods penalize target outputs without modeling their context-dependent
retrieval paths, which can disrupt linguistic structure or suppress benign knowledge. We present ADU, a fine-grained, training-based framework that shifts unlearning from
token erasure to contextual
attention-pathway decoupling. Exploiting the functional distinction between local and global
attention heads, ADU identifies preplan positions that retrieve persistent sensitive anchors and fixes their candidate paths under the original model. It then trains
attention-projection adapters to suppress
attention mass along these paths while preserving local-
attention structure and retain-set
language modeling. Post-training activation exchange tests whether the modified
attention-output module transmits the learned forgetting effect. ADU achieves the strongest aggregate performance among evaluated baselines on the TOFU and WMDP
benchmarks, including a Forget Quality of (0.93) on TOFU. It preserves 87–98% of model utility (92.9% on average versus 81.9% for baselines) while reducing side effects in benign contexts.
Read the full abstract ▾
All authors Xunlei Chen, Qirui Ye, Yuang Li, Yi Gong, Zhaokun Wang, Wenyi Li, Shiyao Guo, Jinyu Guo
Artificial Intelligence · Cross-listed from cs.LG
SplitLite: Low-Rank Residual Compression for Split Learning
Tao Li, Yulin Tang, Qi Guo et al. (+1 more)
Federated fine-tuning of on-device large
language models (LLMs) faces a significant computing burden. To overcome this limitation, split learning (SL) has emerged as a promising solution, which offloads the primary training workload to a powerful server. However, SL requires exchanging high-dimensional activations and gradients between clients and the server, resulting in prohibitive communication costs. To overcome this challenge, we propose SplitLite, a communication-efficient split
federated LoRA fine-tuning method that exploits the low effective rank structure of consecutive-epoch activation and gradient residuals. Our key finding is that, when LoRA uses rank $r$ updates in parameter space, the activation and gradient residuals of the same data sample between adjacent epochs also exhibit effective rank-$2r$ and rank-$4r$ structures, respectively. By revealing this property, SplitLite transmits only quantized truncated singular value decomposition (SVD) residual factors, thereby significantly reducing both activation uplink and gradient downlink traffic. Extensive experiments on the GLUE
benchmark across a series of advanced on-device LLMs demonstrate that our method reduces activation uplink communication costs by up to 93.5% and total communication costs by up to 83.7%, without performance degradation.
Read the full abstract ▾
All authors Tao Li, Yulin Tang, Qi Guo, Xianhao Chen
Artificial Intelligence · Cross-listed from cs.CV
Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG
Zhe Jin, Zhimin Lin, Bin Zheng et al. (+2 more)
Graph-based
retrieval-augmented generation (RAG) provides a scalable paradigm for long-
video understanding, but existing systems typically inherit a fixed temporal granularity from
video segmentation when constructing their
retrieval index. We argue that this design unnecessarily couples indexing granularity with evidence granularity: coarse representations can often suffice for locating relevant temporal regions, while fine-grained evidence remains important for downstream
reasoning. We propose Density-Aware Graph Construction (DAGC), a training-free approach that decouples a query-independent coarse
retrieval index from the original fine-grained evidence space. DAGC constructs a compact, density-adaptive graph index by merging visually redundant neighboring chunks, while preserving mappings to the original temporal units. Retrieved coarse regions are subsequently expanded back to the original chunk granularity for fine-grained evidence refinement and answer generation. Experiments on MLVU, VideoMME, and LongVideoBench show that DAGC retains only about 40–50% of the original graph nodes and achieves $1.3$–$1.7\times$ end-to-end wall-clock acceleration while preserving approximately 99% of the original QA performance. The gains transfer across different LVLM backbones and
video RAG pipelines, suggesting that long-
video RAG need not maintain the same temporal granularity for indexing and evidence
reasoning.
Read the full abstract ▾
All authors Zhe Jin, Zhimin Lin, Bin Zheng, Junhua Fang, Huihua Yang
Artificial Intelligence
PatchWrite: One Line, Not One Section – Compile-Gated, Validity-Preserving Editing for AI-Drafted Manuscripts
Weiwei Yang
Automated manuscript pipelines often regenerate an entire section to repair a local defect, allowing unrelated metrics and citations to change even when the resulting PDF still builds. PatchWrite instead constrains how candidate edits become committed manuscript states: it reuses bounded EDIT N M editing and rollback, but tightens compilation acceptance with fatal-log checks and adds evidence locks that require every cited key and experimental numeric
token to be attested by a reference registry or experimental log. Candidates that fail either check are rejected and the previous HEAD is retained. On a 24-manuscript x 8-fault oracle stress test (768 jobs, evenly split between compile-breaking and content-only faults), whole-slot rewriting mutated an unrelated "12-layer" line in every case (0/192 preserved; numeric Jaccard 0.6667), whereas PatchWrite preserved it in 192/192 cases. Removing the compile gate reduced acceptance to 0, while removing the evidence gate allowed a hallucinated citation to pass. The same pattern held across all eight faults. To test the protocol with generation rather than oracle edits, we reran the 192 jobs with the writer model proposing the edits. The model's candidates were accepted in 75% of cases; nearly all rejections came from one reproducible failure mode in which the model attempted to delete a line using an empty replacement unsupported by the current grammar. Every accepted candidate passed both gates, and 93.75% fixed the injected fault; the remaining cases involved a technically valid but sentence-inappropriate citation and one markup-changing near-miss. In a blind evaluation of sixteen PDF pairs, both raters preferred PatchWrite for preserving lab-grounded facts (C1 Likert 5.0 vs. 2.0), while rating prose quality nearly identically. Logs from 193 in-product drafting tasks show the same classes of failures occurring in practice.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
A Physical Response-and-Memory Model for Muon Optimization
Yinze Hu, Hongjun Xiang, Xingao Gong et al. (+1 more)
Training large
language models is costly. How low a loss the same compute can ultimately reach depends on how each step's gradient is converted into a weight update; the rule that performs this conversion is the optimizer. From SGD and AdamW to the recent
Muon, effective update rules have mostly been shaped by engineering intuition and then selected on
benchmarks.
Muon semi-orthogonalizes the momentum
matrix before applying the update and has kept breaking records on public training
benchmarks; yet why the semi-orthogonalized direction works, and over how long a history the momentum should average, are two questions at present answered mainly by experience. Here we treat the weight
matrix during training as a responsive medium with
memory and build a physical model for it, in which both questions find answers: the semi-orthogonalized direction is the maximally dissipative response under an output-side safety budget, which explains why it works; momentum is the internal stress accumulated by the medium; how long it should average is set by the relaxation of this stress, and a real medium relaxes on more than one timescale, the simplest form being one fast and one slow. On this basis we propose the Bi-Maxwell optimizer. The framework further yields a testable consequence: gradient directions change fast early in training and more slowly later, so the optimal
memory length should grow with training stage; step-by-step measurements of a proxy for it by a read-only probe across 8 independent training trajectories are consistent with this consequence. Replacing the
memory kernel alone, from a single timescale to two, brings training to the target loss in noticeably fewer steps on a public large-
language-model optimizer
benchmark.
Read the full abstract ▾
All authors Yinze Hu, Hongjun Xiang, Xingao Gong, Hongyu Yu
Artificial Intelligence · Cross-listed from cs.IR
Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval
Kishore Konda
Dense vector
retrieval has become the foundation of modern semantic search, yet existing approximate nearest neighbor (ANN) indexes treat an
embedding as an indivisible point in a high-dimensional space. In this work, we propose the Hypergraph
Embedding Index (HEI), a framework that instead organizes documents according to combinations of highly activated latent
embedding dimensions. This formulation enables inverted-index style candidate generation while preserving the semantic ranking capabilities of dense
embeddings. We further demonstrate that constructing multiple complementary hypergraphs substantially improves
retrieval coverage without the combinatorial growth associated with increasing the dimensionality of a single hypergraph. Finally, we establish that the statistical properties of
embedding activations strongly influence coordinate-inverted indexing efficiency, introducing activation diversity as a diagnostic metric governing
embedding indexability in coordinate-inverted frameworks.
Read the full abstract ▾
Artificial Intelligence
SA-RSQ: A Versatile Sparse Representation Framework for Multi-modal Recommender Systems
Xiang Wang, Shigang Quan, Tingzhen Chang et al. (+5 more)
Deploying high-dimensional
multimodal features in industrial recommender systems incurs substantial storage and latency overhead. Hard quantization is compact but introduces boundary distortion, whereas dense soft quantization couples representation quality to the limited storage budget. We propose Sparse Activation-based Residual Soft Quantization (SA-RSQ), which uses Top-K sparse routing and softmax weights to store compact (Index, Probability) tuples. The stored tuples decouple per-item storage from codebook dimensionality; for a fixed selected support, gradients propagate through the routing weights and weighted reconstruction without relying on a straight-through
estimator. Experiments on a proprietary food-delivery advertising
dataset show favorable reconstruction-performance and CTR trade-offs across storage budgets of 8-48 bytes per item. A preliminary Next-Distribution Prediction study and a one-week online A/B test further demonstrate the practical potential of SA-RSQ, with relative lifts of +2.51% in CTR and +3.66% in CPM.
Read the full abstract ▾
All authors Xiang Wang, Shigang Quan, Tingzhen Chang, Kang Yang, Sitong Chen, Yabo Fan, Xingxing Wang, Zhaodian He
Artificial Intelligence
Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B
Defu Lin, Wenhui Chen, Ziyao Lin et al. (+3 more)
Embodied multimodal agents must answer from growing observation streams under a fixed per-decision
token budget. We formalize this constraint through four resource walls: a perceptual Shannon wall for bounded state, a horizon wall for query-independent frame selection, a round wall for non-adaptive
retrieval, and a conditional composition wall for fixed-depth inference. We introduce ASP, a training-free wrapper for frozen
multimodal models that combines a capped structured state, a verbatim episodic index, and query-conditioned budget allocation with iterative access. Following a pre-registered protocol, we evaluate seven open-weight models from 3B to 31B on SEW-Bench, a license-free synthetic long-horizon walkthrough
benchmark constructed to instantiate these walls. The registered natural-
video benchmarks were not run because their frames require
dataset agreements; our evidence therefore concerns access mechanisms, not natural-scene perception. Under a 4,096-
token decision budget, ASP reaches 75 to 94% episodic
retrieval accuracy, compared with 3 to 19% for equal-budget query-independent sampling, and budget reallocation outperforms quadrupling the sampling budget on every backbone. However, the full three-component architecture does not validate channel duality: removing the compressive state raises the flagship mean from 35.4 to 58.0, ASP does not outperform the verbatim-only baseline on any backbone, and two of four pre-registered falsification criteria fire. These results show that query-conditioned access, rather than parameter count or context growth alone, is decisive under a fixed budget, while prompted online compression does not earn its cost in this setting.
Read the full abstract ▾
All authors Defu Lin, Wenhui Chen, Ziyao Lin, Jianlin Chen, Peiji Long, Chi Man Vong
Artificial Intelligence
Toward Effective and Reliable LLM Agents via Dynamic Ontology
Xiaohui Zhang, Zequn Sun, Chengyuan Yang et al. (+3 more)
Large
language model (LLM)
agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks, this leaves important semantic connections implicit. This often results in incomplete evidence use and brittle multi-step decisions. Ontologies offer a way to externalize domain concepts and relations as machine-interpretable structures, but constructing task-usable ontologies traditionally requires substantial effort from domain experts and is difficult to scale. Automatic construction is also challenging: an ontology that appears semantically plausible may not contain the relational structures needed for actual decision making. We present OaK, an ontology-as-a-kernel framework that dynamically constructs and refines task-oriented ontologies for LLM
agents. Given task requirements and training data, OaK constructs an ontology and its knowledge graph, generates task-adaptation functions for graph
reasoning, and uses judge feedback to iteratively refine both. By making relevant concepts and relations explicit, the ontology grounds knowledge
retrieval and multi-step decision making. We evaluate OaK on TravelPlanner, CRMArenaPro, and ToolQA. Results show that OaK improves standard LLM
agents, strengthens evidence grounding, and boosts the reliability of multi-step
reasoning.
Read the full abstract ▾
All authors Xiaohui Zhang, Zequn Sun, Chengyuan Yang, Yuanning Cui, Lingbing Guo, Wei Hu
Artificial Intelligence
ParallelWorld: Test-Time Scaling for Agentic Embodied Reasoning
Min Chen, Shengjun Zhang, Yuxin Li et al. (+4 more)
Embodied AI has emerged as a key paradigm for autonomous systems operating in complex physical environments. While end-to-end models have established strong local capabilities for perception and control, scaling these capabilities to extended, multi-stage tasks remains difficult. Agentic
embodied systems address this challenge by introducing high-level planners that organize perception,
reasoning, and executable skills over longer interaction horizons. However, existing agentic
embodied frameworks typically generate actions for direct execution without explicitly simulating how alternative action sequences shape future observations and task progress, leading
agents to commit to suboptimal interactions before considering their long-term consequences. To address this limitation, we propose ParallelWorld, an adaptive-horizon test-time scaling framework that grounds agentic
embodied reasoning in the prospective simulation of action outcomes. Specifically, we design an
agent system to simulate and evaluate alternative trajectories in parallel before committing to an action. A verifier assesses intermediate state transitions with respect to the task objective, dynamically
pruning unpromising branches and guiding subsequent expansion. Based on the evaluated long-horizon outcomes, the
agent selects a trajectory, executes only its first action, and replans as new observations become available. Experiments on ESI-Bench and LIBERO-Pro demonstrate improvements in active spatial
reasoning and
language-conditioned manipulation, respectively, highlighting the effectiveness of prospective planning for both understanding and manipulation tasks.
Read the full abstract ▾
All authors Min Chen, Shengjun Zhang, Yuxin Li, Zhang Zhang, Xin Fei, Chong Xia, Yueqi Duan
Artificial Intelligence
Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents
Yuchen Huang, Sijia Li, Jun Zhang et al. (+1 more)
Multimodal Large
Language Models (MLLMs) are increasingly deployed as multi-step
agents, where explicit
reasoning supports task decomposition and tool coordination but also accumulates self-generated text. Over long trajectories, this text can dominate the context and suppress visual evidence, creating textual debt. We observe that
reasoning becomes redundant once task-relevant visual evidence is grounded, while stale hypotheses can misguide later inference when grounding remains uncertain.
Pruning must therefore remove redundant text without discarding visual evidence. We propose SPARE, a Kullback-Leibler (KL)-guided framework for
pruning accumulated
reasoning in
multimodal tool-use
agents. SPARE uses a compact task-state summary as privileged diagnostic context. For each candidate segment, it replays the same model under the original and summary-conditioned contexts. Reverse-KL divergence from on-policy self-
distillation (OPSD) then tests whether the summary sufficiently covers the segment without disrupting future
reasoning. We further fine-tune the summarizer with supervised fine-tuning (SFT), enabling more compact summaries, broader coverage, and more aggressive
pruning. Across multi-step visual tool-use
benchmarks, SPARE achieves the highest average accuracy among
pruning methods while removing 37.89-64.58% of
reasoning tokens. This favorable accuracy-context trade-off shows that reducing textual dominance restores reliance on visual evidence and mitigates over-conditioning on self-generated
language.
Read the full abstract ▾
All authors Yuchen Huang, Sijia Li, Jun Zhang, Yi R. Fung
Artificial Intelligence
What Process Evaluation of Coding Agents Actually Measures: Action, Task, and Step Are Three Different Levels
Jiawei He, Mengyu Shi, Jie jia et al. (+2 more)
Coding
agents are increasingly evaluated not only by whether they solve a task, but also by how they execute it. However, existing process-level evaluations often treat action prediction, task uncertainty, and step attribution as if they were the same problem, which makes it unclear what such evaluations actually measure. In this paper, we introduce a measurement framework for process evaluation in coding
agents and instantiate step-level causal attribution with SCAE, a replay-based
estimator derived from a structural causal model of
agent execution. Our framework combines prefix-conditioned identification, replay/intervention-based estimation, and controlled judge-information manipulation to study process evaluation at the action, task, and step levels. Experiments on 499 file-localization episodes from 12 repositories show that next actions are driven primarily by execution provenance rather than code-graph transitions, execution uncertainty is structured at the task rather than step level, and full-trace judges exhibit systematic
collider bias, suggesting that current process evaluation often measures semantic relevance rather than certified causal contribution.
Read the full abstract ▾
All authors Jiawei He, Mengyu Shi, Jie jia, Xikai Yang, Dong Sun
Artificial Intelligence · Cross-listed from cs.CV
WildHandBench: A Benchmark for Handwritten Text Understanding that Challenges MLLMs and Humans
Jun Zhang, Qiao Zhao, Cheng Cui et al. (+6 more)
While the top model on OmniDocBench now reaches 96.34% overall on printed-document parsing, the ability of current models to handle challenging handwritten documents remains largely uncharacterized. Existing
benchmarks focus on isolated text or formulas, overlook handwritten tables and real-world degradation, and report aggregate accuracy without explaining why models fail. We present WildHandBench, a
benchmark containing 500 handwritten documents across three structures (free text, tables, formulas), four
languages, and nine real-world scenarios. We introduce a Prior-Driven Error (PDE) metric that quantifies whether errors originate from
language priors rather than visual evidence. Evaluating 18 state-of-the-art models together with calibrated human baselines, we find: (1) the best model achieves only 71.85% overall; (2) humans outperform all models yet the gap is narrow (77.09% vs. 71.85%); and (3) model errors are qualitatively different from human errors – 63-91% of model errors are prior-driven versus only 49% for humans, exposing systematic reliance on
language priors that conventional accuracy metrics cannot capture.
Read the full abstract ▾
All authors Jun Zhang, Qiao Zhao, Cheng Cui, Jianying Qu, Zhongkai Sun, Jianwen Yang, Changda Zhou, ZhuoXin Liu, Shubin Han
Artificial Intelligence · Cross-listed from cs.CL
What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation
Ziyue Wang, Aomufei Yuan, Yiran Yao et al. (+10 more)
Large
language models are increasingly used to propose research ideas, yet the prevailing ways of judging such ideas supply no shared decision rule: free-form judging sways with style and position, and scoring against a later paper rewards recovery of one realized trajectory. We introduce a
benchmark that carries a proposal from Literature to Test: the Lit2Test
benchmark centers on a six-field contract organized around a falsifying outcome, so that every proposal precommits the observation that would prove it wrong, making its quality decidable in the first place rather than merely arguable. Built prospectively from 200 real-paper neighborhoods, Lit2Test elicits proposals from four frontier models and compares them through 1,200 pairwise comparisons judged blind in both presentation orders. The protocol audits its own reliability through diagnostic controls and bounded human calibration, with three annotators corroborating the conclusions within explicitly stated reliability bounds. Lit2Test recovers a strict ranking of the four models in all 10,000 bootstrap replicates, and the separation comes from the quality of the proposed tests and metrics rather than from surface fluency. We release the
benchmark, construction pipeline, and audit artifacts for public use.
Read the full abstract ▾
All authors Ziyue Wang, Aomufei Yuan, Yiran Yao, Linli Yao, Hongyao Zuo, Ziwen Gong, Yuanxin Liu, Shicheng Li, Yishuo Cai, Tong Yang, Xu Sun, Xiaohui Li, Haoli Bai
Artificial Intelligence
Concepts for Securing Agentic AI Coding and the Terok Environment
Jiří Vyskočil, Franz Pöschel and Andreas Knüpfer
Agentic AI is a fascinating new tool for software development. It is a huge step forward compared to "conventional" AI assisted coding, which in turn was a considerable breakthrough earlier. AI support through LLMs is a young and very fast-moving field. The "conventional" (non-agentic)
flavor became useful and productive in early 2025 (around 18 months ago) and the agentic
flavor followed in fall 2025 (approximately 9 months ago). Besides all its benefits and potential, it also carries some fundamental risks for IT security. And the agentic approach added very severe risks while making others much more dangerous. With all the motivation to explore this fascinating new tool we should not ignore the risks but actively address them. We present (I) an assessment of the IT security risks, (II) a concept for mitigating them without breaking its benefits, and (III) an overview about an implementation of our concept. In this very dynamic field this is likely not the final and once-and-for-all answer to the identified issues but still a substantial step forward in responsible usage of Agentic AI for software development. It should also be a contribution to the community to allow early and eager evaluation of the potential of agentic AI for software development without actually suffering from its implied IT security risks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IT
Deep Learning-Based Multi-User Communication Design for Dense IoT Networks: Interference-Aware Finite-Blocklength Communication and Preliminary MIMO Extensions
Arkadeep Sinha, Shubham Paul and R. Manivasakan
Dense IoT networks require reliable communication despite limited spectrum and substantial multi-user interference while maintaining manageable receiver complexity. This work introduces a deep-learning-based end-to-end multi-user communication design for interference-limited finite-blocklength IoT scenarios, focusing on short and medium blocklengths. We extend a prior 2-user SiameseNet transceiver framework to accommodate 2, 4, and 8 users, leveraging learned redundancy for interference suppression and noise robustness. Compared to conventional non-orthogonal access baselines, our method demonstrates strong Block Error Rate (BLER) performance across various scenarios without resorting to joint detection; the per-user decoder scales roughly linearly with the number of users. Further, we examine the robustness under interference mismatch and unequal interference strengths, critical for practical deployments with heterogeneous devices. The Latent-space analysis reveals that the learned codeword distance increases as the effective per-user rate decreases, corroborating with the observed BLER improvements. In addition, we also present preliminary results for a 2X2
MIMO setup under fixed-channel CSIT and CSIR, indicating potential for extending the framework to IoT gateways with multiple
antennas.
Read the full abstract ▾
Artificial Intelligence
Beyond Observed Auxiliary Relations: Environment-Conditioned Modeling for Multi-Behavior Recommendation
Seunghan Lee, Hyunsik Yoo, Jian Kang et al. (+2 more)
Multi-behavior recommendation (MBR) leverages auxiliary behavioral signals, such as clicks and add-to-cart, to enhance target behavior prediction like purchases. While recent graph neural network-based approaches have achieved strong performance by systematically propagating auxiliary behavior signals, they still suffer from two fundamental challenges inherent to auxiliary behaviors: (1) missing auxiliary signals, which hinder generalization to items without auxiliary observations, and (2) unreliable auxiliary signals, which amplify noise misaligned with the target behavior. To address these challenges in a unified manner, we propose BOAR, an environment-conditioned MBR framework that addresses missing and unreliable auxiliary signals through two complementary modules conditioned on auxiliary observability. Extensive experiments demonstrate that BOAR consistently outperforms state-of-the-art baselines, achieving up to 7.82% gains in HR@10 overall and up to 44.2% gains for target items without auxiliary observations, highlighting its ability to capture hidden preferences beyond observed auxiliary relations. Our code is available at: https://github.com/LSH0411/BOAR.
Read the full abstract ▾
All authors Seunghan Lee, Hyunsik Yoo, Jian Kang, Susik Yoon, SeongKu Kang
Artificial Intelligence · Cross-listed from cs.LG
Safety Hacking in Constrained Best-of-$N$ Inference-time Scaling
Akifumi Wachi, Takumi Tanabe and Youhei Akimoto
Inference-time pipelines often sample multiple outputs, filter them with a learned safety model, and return the proxy-feasible output with the highest learned reward. We show that this composition creates a two-stage failure: an imperfect safety proxy first contaminates the feasible set with unsafe outputs, and reward maximization can then amplify this residual contamination. We define safety hacking as selecting an output that passes the learned constraint but violates the true safety criterion. For constrained Best-of-$N$ sampling, we derive finite-$N$ bounds governed by the joint upper reward tails of safe and unsafe outputs within the proxy-feasible set. If unsafe-but-feasible outputs have the heavier tail, safety hacking becomes asymptotically certain as $N$ grows, even when false-positive mass and average safety- and reward-proxy errors are arbitrarily small. We also show that policies within a bounded $\chi^2$ divergence from the proxy-feasible reference distribution admit an $N$-independent safety-hacking bound, and instantiate this general coverage-control principle with constrained pessimistic sampling. Coverage control limits amplification but cannot repair a contaminated feasible set: admitted unsafe outputs may still be favored, and regularized selection is not necessarily safer than constrained Best-of-$N$ for every reward proxy. Toy and
language-model experiments characterize both contamination and its reward-tail amplification, which exposes an inherent difficulty in inference-time scaling with learned safety models.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text
Hyeonyu Kim, Hwayeon Kim, Youngwon Choi et al. (+2 more)
Spoken
Language Models (SLMs) generate textual responses directly from
speech, offering an alternative to cascaded systems. Despite recent advances, existing SLMs still exhibit weaker instruction-following behavior and limited generalization across diverse tasks compared to text-based
language models. Our analysis shows that
speech and text representations in current SLMs remain weakly aligned despite strong downstream performance, indicating that structural differences between continuous, temporally varying
speech and discrete text remain insufficiently addressed. To address this, we propose a simple framework that decouples length mismatch from semantic
alignment and encourages closer correspondence between
speech and text representations. Experiments across multiple
benchmarks demonstrate competitive performance against strong baselines, underscoring the importance of explicitly addressing structural differences between
speech and text in SLM training. Our code is publicly available at https://github.com/jaykim9870/Do_SLMs_Hear_
Speech_as_They_Read_Text.
Read the full abstract ▾
All authors Hyeonyu Kim, Hwayeon Kim, Youngwon Choi, Myeongkyun Cho, Huu-Kim Nguyen
Artificial Intelligence
CDEG: Learning Decision-Critical Evidence for Long-Horizon Diagnostic Agents
Xiwei Dai, Zijie Meng, Zhiting Fan et al. (+4 more)
Unlike static medical question answering, long-horizon diagnosis captures the sequential nature of clinical practice: evidence is progressively acquired, integrated, and evaluated over multiple rounds of interaction before reaching a final diagnosis. However, existing doctor
agents often fail when critical evidence is either not acquired or not adequately incorporated into diagnostic
reasoning. Recent agentic approaches attempt to address these failures by reusing historical trajectories or distilled
memories. But their diagnostic gains remain constrained because such experience may contain noisy or incidental information and is typically reused without validating which evidence actually drives diagnostic decisions. To address this limitation, we introduce CDEG, a graph-based framework that learns reusable decision-critical evidence from historical diagnostic trajectories. CDEG contrasts successful and failed trajectories from the same case to identify candidate evidence, validates their diagnostic impact through controlled counterfactual interventions, and organizes the resulting diagnosis–evidence–action relations into a structured graph. During inference, CDEG tracks the evolving patient evidence state to retrieve relevant diagnostic relations and selectively guide missing evidence acquisition or overlooked evidence reappraisal. Across in-domain and out-of-distribution
benchmarks with multiple doctor
agent backbones, CDEG consistently improves diagnostic performance, achieving up to an 11.5% accuracy gain over vanilla
agents. These results demonstrate that reliable long-horizon diagnosis requires moving beyond trajectory-level experience reuse toward evidence-level learning of the factors that truly shape clinical decisions.
Read the full abstract ▾
All authors Xiwei Dai, Zijie Meng, Zhiting Fan, Yixuan Tang, Guanyu Jiang, Ziru Niu, Zuozhu Liu
Artificial Intelligence · Cross-listed from cs.CL
AraDetox: A Multi-Dialect Arabic Detoxification Dataset
Mo El-Haj
Arabic harmful-
language detection has received considerable
attention, yet Arabic text detoxification remains underexplored. We introduce AraDetox, a multi-dialect Arabic detoxification
dataset comprising 10,500 harmful social-media posts and 84,000 detoxified rewrites generated using GPT-5 and Gemini 2.5 Flash across Modern Standard Arabic, Gulf, Levantine, and Egyptian Arabic. The generated outputs were assessed through human evaluation and automatic analyses of lexical change, semantic preservation, sentiment, and dialectal style. Results show that detoxification is primarily a meaning-preserving rewriting task: substantial lexical and structural reformulation is accompanied by consistently high semantic similarity. Human evaluation confirms successful harmful-
language removal while largely preserving the original meaning. Dialectal analyses further indicate that the generated variants exhibit measurable stylistic
alignment with reference Arabic dialect corpora. Comparison with existing resources highlights two complementary approaches to detoxification: minimal-edit lexical substitution and meaning-preserving reformulation. Our findings demonstrate that large-scale Arabic detoxification resources can be constructed through LLM-assisted generation and human verification. The
dataset is publicly available at https://github.com/ArabicNLP-UK/AraDetox to support future research on Arabic detoxification, safe text generation, and multi-dialect Arabic NLP.
Read the full abstract ▾
Artificial Intelligence
Language Models Give Group-Linked Fields the Wrong Weight
Zengqing Wu and Chuan Xiao
Large
language models are increasingly used to judge people, and their answers can depend on inputs correlated with a protected attribute such as race, even when that attribute is never shown. Interpreting this reliance requires knowing how much predictive information those inputs add, but audits often report only whether a decision changes. We introduce an evidence-referenced audit that compares proxy reliance with two references, the known outcome rule and a
Bayesian linear regression fitted to the same labeled examples, while measuring ranking accuracy separately. We apply it to four models in a simulated patient-ranking task with known field weights. We find four results. First, at zero predictive value, the models still relied on fields that carried no information, while the same-example learner did not. Second, as proxies became predictive, reliance grew far less than the reference. Third, display format mattered. Ordered labels drew more reliance than arbitrary labels, a direction that held in all four models. Fourth, ranking accuracy did not consistently track these changes in reliance. Based on these findings, we argue that decision changes and accuracy cannot show whether proxy reliance is warranted by the evidence. Audits should report reliance against an explicit predictive reference, alongside accuracy. Ordered fields whose values move with group membership, such as scores or income bands, are a useful starting point. Together, these results make it possible to measure how far reliance departs from the evidence, rather than infer it from observed choices alone.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
The Mask Is Not the Model: Auditing Prefix Invariance in Attention, State-Space, and Hybrid Sequence Models
Taebong Kim, Youngsik Hong, Minsik Kim et al. (+3 more)
Hybrid sequence models must satisfy prefix invariance: representations at position t must not depend on future inputs, yet this is rarely verified. We formalize prefix invariance and give a lightweight audit, two forward passes, no training or gradients, yielding a per-layer score localizing where causality breaks.
Attention-mask inspection, the field's default check, is incomplete: causality is a graph-level property, and leaks can occur via scans, aggregations, or normalization despite correct masks. Across 192 injected-fault trials on eight checkpoints, mask inspection detected none, while our audit localized all 192/192 to the exact layer. Static/dynamic analysis of chunked-scan code in
transformers found the same defect in Zamba2 and Nemotron-H, an inter-chunk axis error fixed via the reference implementation. The method fits on one page and runs in seconds.
Read the full abstract ▾
All authors Taebong Kim, Youngsik Hong, Minsik Kim, Sunyoung Choi, Jaewon Jang, Minseo Kim
Artificial Intelligence
Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron
Sahong Park, Suhwan Park, Hoyoung Lee et al. (+8 more)
Large
language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific investment preferences. We study whether a model's overall investment stance can be calibrated to a specified direction and strength. We introduce an investment-bias dial, an inference-time intervention on a single
neuron that continuously adjusts a model-level decision prior—its overall tendency toward buying or selling—without targeting specific firms or investment attributes. Using matched positive and negative evidence, we evaluate five open-weight LLMs and find that the dial produces monotonic changes in investment stance without modifying
prompts or model parameters. At the response level, the dial shifts both investment decisions and the evidential emphasis of generated rationales under identical inputs. In an agentic
retrieval setting, the dial also changes what information the model searches for, which evidence it selects, and which evidence is reflected in its final analysis. In a long-context evaluation, the dial maintains stable stance control as context length increases, whereas a matched system-
prompt instruction progressively attenuates. We further show that changes in the dial propagate to security rankings and downstream portfolio composition in an exploratory backtest. Overall, our results show that an LLM's aggregate investment stance can be calibrated toward a specified target at inference time.
Read the full abstract ▾
All authors Sahong Park, Suhwan Park, Hoyoung Lee, Gakyung Kwon, Wonbin Ahn, Jaewon Choi, Alejandro Lopez-Lira, Yoon Kim, Chanyeol Choi, Hyeongwoo Kong, Yongjae Lee
Artificial Intelligence
GSAR: Goal-State-Anchor Rewards for Mobile GUI Agents with Self-Evolving Data Synthesis
Long Zhang, Yuhan Chen, Chaoran Zhang et al. (+7 more)
Vision-
Language Models (VLMs) based GUI
agents stand to benefit significantly from online reinforcement learning (RL). However, their training is bottlenecked by two fundamental issues: current data synthesis methods for GUI
Agents rely on specific environments and struggle to generate diverse data, while existing evaluators either suffer from limited scalability or provide inaccurate and unreliable reward signals. To overcome these challenges, we introduce GSAR (Goal-State-Anchor Reward), a RL reward framework that supports scalable task generation and delivers reliable reward signals for stable and efficient policy optimization. Our approach features self-evolving data synthesis, which produces multiple environments through task execution and generates diverse tasks and goal states. Complementing this, a state-anchor mechanism automatically annotates task-relevant UI elements in successful goal states as reference anchors. During RL training, these reference anchors provide accurate, scalable reward signals that substantially enhance efficiency. Extensive evaluations demonstrate that our framework achieves over 90% accuracy on offline trajectory verification and performs closest to rule-based methods. Furthermore,
agents trained using our reward framework exhibit strong performance on both AndroidWorld and our constructed
benchmark, establishing a scalable approach for GUI
agent training.
Read the full abstract ▾
All authors Long Zhang, Yuhan Chen, Chaoran Zhang, Wanxia Cao, Kun Huang, Pengzhi Gao, Wei Liu, Jian Luan, Chenliang Li, Lixin Zou
Artificial Intelligence
FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks
Hang Wang, Jin Zhang, Guoliang Xu et al. (+13 more)
Financial document parsing requires accuracy, structural consistency, and verifiability that current
benchmarks often fail to reflect. We present FinixDoc, an end-to-end agentic parsing system for real-world financial documents, with FinixDoc-VL, a 4B-scale
vision-
language model built on Qwen3-VL-4B, as its core parser. To characterize the gap between
benchmark and deployment performance, we introduce a Document Parsing Capability
Matrix organized along two practical axes: visual quality and document scale. Guided by this
matrix, FinixDoc-VL is trained with a domain-adapted recipe combining homoglyph-aware contrastive learning and multi-stage reinforcement learning with composite domain-specific rewards. To better leverage our accumulated advantage in low-quality financial-document data and support large-scale, high-quality data production, we further build a human-in-the-loop Data Factory pipeline with confidence-aware expert review. For evaluation, we construct FinixDocBench, a financial-domain evaluation suite covering digital-native, camera-captured, ultra-large-page, and internal-workflow scenarios, with a compliance-reviewed subset released alongside this technical report. On its main subsets, FinixDoc-VL achieves the highest overall score (81.43) among evaluated baselines, outperforming the next-best open-source model by 5.13 points, with the largest gains on internal financial workflows (FinixInner: 84.08 vs. 78.73).
Read the full abstract ▾
All authors Hang Wang, Jin Zhang, Guoliang Xu, Pengyue Lu, Yao Li, Zijiao Zhang, Tianyu Huang, Weiqi Xiong, Yulong Wang, Chuqiao Lu, Wenkang Huang, Kai Yang, Yadong Li, Hui Li, Xingzhong Xu, Xiao Xu
Artificial Intelligence · Cross-listed from cs.LG
Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning
Shuting Xie, Nathaniel Lesperance and Graham W. Taylor
Large
language models (LLMs) are increasingly used for scientific decision support, yet reliable confidence estimation remains difficult in black-box settings. We study uncertainty estimation for hierarchical taxonomic
reasoning generated by a black-box LLM in a long-tailed biodiversity monitoring pipeline. Using proxy features extracted by an open-source tool LLM, we train lightweight supervised
estimators with hierarchy-aware supervision to predict rank-wise correctness. Across three tool LLMs, the supervised
estimators consistently outperform a
token-likelihood baseline for micro discrimination and selective prediction under a single global rejection threshold, improving micro AUROC from 0.57 to 0.75–0.80. The best results are achieved by a rank-specific multi-head design (H3), suggesting that accounting for hierarchical output structure is important when a unified abstention rule is required. Our code is publicly available at https://github.com/uoguelph-mlrg/hierarchy-aware-llm-uq
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.MA
Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments
Ryuki Hyodo
Large
language models (LLMs) and
vision-
language models (VLMs) are expanding the range of behaviors that can be represented in
agent-based simulations, but many contemporary platforms are difficult to study, modify, or run on ordinary computers. We present two intentionally minimal simulation foundations for education and rapid prototyping. SD-AgentFoundry-2D provides a two-dimensional multi-
agent environment in which locally hosted LLM
agents move, communicate, respond to place occupancy, and encounter spatially localized fire events. SD-AgentFoundry-3D provides a three-dimensional digital-twin environment in which a locally hosted VLM receives first-person images and produces natural-
language movement instructions. Both codebases are designed to run locally on macOS, Windows, and Linux and are deliberately left open to modification rather than developed as finished applications. Together, they offer accessible starting points for learning about generative social simulation and for building domain-specific extensions.
Read the full abstract ▾