Artificial Intelligence
Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models
Ilias Kazantzidis, Timothy J. Norman, Yali Du et al. (+1 more)
We address the problem of safely training an
agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown and no suitable reward function is available. In the context of safety-critical environments, we consider traditional reinforcement learning impractical and resort to the resource of human input. We introduce DROPJ, a human-centred method for both safe training and deployment. We first learn a world model (a learned simulator) from a
dataset of prior real-world trajectories. A human then plays the game in this learned simulator to extract several informative simulated trajectories. From these, we sample pairs of simulated trajectory segments and elicit from a human their preference over these segments, as well as a reason (justification) for their choice. We then train a reward model from these justified preferences and use it, together with the world model, to directly deploy the
agent using model predictive control. Running real-user experiments, we find that generating informative simulated trajectories from a user significantly reduces the computational cost during training compared to other strategies, and can also improve the performance during deployment. In the context of training within a learned simulator, we show that the use of preferences rather than other types of feedback substantially improves the performance during deployment. We further demonstrate that safety justifications accompanying preferences can significantly enhance safety or prioritise user-prescribed aspects of safety associated with them during deployment.
Read the full abstract ▾
All authors Ilias Kazantzidis, Timothy J. Norman, Yali Du, Christopher T. Freeman
Artificial Intelligence · Cross-listed from cs.CL
What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors
Winston Zeng, Ali Emami and Jinho D. Choi
What a
language model will and will not do is largely set during post-training, but which behaviors it expresses, hides, or resists is not revealed by prompting alone. Persona vectors, behavioral directions in activation space, can probe this organization, but prior work covers only a handful of traits. We present the first systematic application of persona vectors at this scale, compiling a 53-trait inventory across four behaviorally distinct domains and labeling every trait in two open-weight models as natural (expressed at baseline), steerable latent but amplifiable, or intractable (resistant to standard extraction). Both models default to helpful, task-oriented behavior: all nine agentic traits are natural, and their default clinician behavior matches a board-certified psychologist's independent desirability judgments on 16 of 17 traits. Steering produces its largest gains on traits these defaults exclude: hyperbole,
hallucination, and sycophancy. The same asymmetry holds across all 171 generic-trait pairs: two steerable traits can collapse the composition, but pairs involving a default never do. Where standard extraction fails on a trait like "evil," a vector transferred from a fine-tuned variant still recovers it, with the residual refusals appearing inside the model's chain-of-thought. Persona vectors are most informative not as a set of controls but as a probe of behavioral organization.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IT
Active Beyond-Diagonal RIS Empowered Heterogeneous Edge Computing: A Distributional Reinforcement Learning Approach
Tianyu Pang and Hongyu Li
Active beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) enables hybrid transmitting and reflecting mode to achieve effective signal amplification and full-space coverage, thus providing a promising solution for blockage-aware uplink offloading in heterogeneous mobile edge computing (MEC) systems. However, practical hybrid mode active BD-RIS are realized by reciprocal devices, which inherently generate cross-sector energy leakage that will reshape the system-level energy-latency tradeoff. This paper studies energy-aware offloading and resource allocation for reciprocal active BD-RIS-assisted heterogeneous MEC, where offloading decisions, CPU/GPU computation allocation, transmit powers, receive processing, and active BD-RIS are tightly coupled. The resulting problem is a high-dimensional mixed integer nonconvex problem and is difficult to solve efficiently by conventional per-instance optimization. To address this challenge, we develop an end-to-end joint optimization framework based on a refined version of the distributional soft actor–critic
algorithm, named as DSAC-T. By modeling return distributions rather than only expected values, DSAC-T improves policy stability under reward heterogeneity and feasibility-boundary sensitivity. Compared with other baseline
algorithms, DSAC-T achieves the best energy-latency reward, the highest feasibility ratio of 81.67%, and a fast online decision time of 0.0267 s per scenario.
Read the full abstract ▾
Artificial Intelligence
Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents
Richmond Alake, Cesare Bernardis, Paul Cayet et al. (+10 more)
Agent memory is a systems problem for long-horizon
agents. Practical deployments require retention of task state across extended conversations, recovery of user-specific facts and preferences across sessions, and accumulation of procedural knowledge from prior outcomes. These requirements extend beyond document
retrieval: a
memory layer must determine which interactions become durable state, how that state is scoped, how it is retrieved under latency constraints, and how it is revised or removed over time. This report studies Oracle
Agent Memory as a database-native
memory substrate built on Oracle Database. Three themes organize the discussion:
memory as a lifecycle spanning ingestion, extraction, consolidation,
retrieval, summarization, and revision or removal; a layered architecture that separates an active
memory core from a passive
memory-store interface with explicit scope control across users,
agents, and threads; and evaluation methodology in which downstream task accuracy is complemented by
memory-centric measures such as evidence
retrieval, recall, latency, and estimated
token use. The report summarizes LongMemEval results, reaching 93.8% accuracy, compares Oracle
Agent Memory against flat-history baselines, using about 10.7x fewer
tokens, and published or reported external baselines where available, and closes with implementation-oriented appendix material covering setup, thread lifecycle, and search semantics.
Read the full abstract ▾
All authors Richmond Alake, Cesare Bernardis, Paul Cayet, Luca Engel, Damien Hilloulin, Sungpack Hong, Allen Hosler, Nickolas Kavantzas, Ingo Kossyk, Son Le, Rhicheek Patra, Kartik Talamadupula, Valentin Venzin
Artificial Intelligence · Cross-listed from cs.CV
Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget
Guoxuan Chen, Chufeng Xiao, Haoran Yang et al. (+30 more)
We introduce Boogu-Image-0.1, an open-source unified
multimodal understanding and generation model family, comprising Base, Turbo, Edit, and Edit-Turbo variants. It delivers competitive performance in high-quality text-to-image generation, fast inference, instruction-based editing, and bilingual (Chinese-English) text rendering. Closed-source
multimodal systems like Nano-Banana-Pro and GPT-Image-2 achieve strong performance through system-level integration rather than a single model, yet their internal practices remain largely undisclosed. In this work, we demonstrate that strengthening the understanding capability of the system, through a stronger
multimodal encoder, agentic
prompt rewriting, and related techniques, together with improvements in data quality, training pipelines, and agentic inference-time scaling, can substantially enhance generation and editing performance even under highly constrained compute budgets. Comprehensive evaluations show that Boogu-Image-0.1 consistently matches or surpasses other open-source models across standard
benchmarks, and achieves results approaching leading closed-source systems. Notably, this is accomplished with only 208.62 million unique images. The base model's theoretical training cost is only approximately \$400K. We share practical discussions that we believe are valuable to the broader research community, and release weights, code, and recipes under Apache 2.0 to advance the open ecosystem for unified
multimodal understanding and generation. Our code is available here: https://github.com/Boogu-Project/Boogu-Image.
Read the full abstract ▾
All authors Guoxuan Chen, Chufeng Xiao, Haoran Yang, Siyue Xie, Binxiao Huang, Ming Zhang, Cheuk Him Chau, Xinyu Fu, Yingzhao Lian, Tom S.Y. Li, Jintao Lin, Bowen Dong, Zian Qian, Yuhao Liu, Yuxuan Hu, Weikang Shi, Bin Zou, Bowen Zheng, Haoxuan Che, Chang Chen, Yuyang He, Heyang Sun, Tianyu Huang, Chong Hou Choi, Cheng Gong, Han Shi, Haoli Bai, Xihui Liu, Hongsheng Li, Qifeng Chen, Chao Huang, Rui Liu, Chenyang Lei
Artificial Intelligence · Cross-listed from cs.LG
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Qingyu Zhang, Qianhao Yuan, Hongyu Lin et al. (+5 more)
Structured
pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse on the free-form generation that deployment actually requires. Two observations trace this gap. First, greedy pass@$1$ nearly vanishes after compression, yet pass@$k$ recovers substantially under repeated sampling: useful generations are demoted, not erased. Second, the recoverable regime fails mainly through suffix repetition. Recovery should therefore train on the compressed model's own on-policy states with dense
token-level supervision, which On-Policy
Distillation (OPD) provides by reusing the pre-compression model as a frozen teacher. However, long on-policy rollouts spend early recovery budget on low-information repetitive suffixes, delaying loss descent. To mitigate this waste, we propose \shortopd, a short-to-long OPD schedule that detects teacher-confirmed repetitive suffixes, treats the surviving prefix as each rollout's effective length, and allocates future rollout budgets to the effective lengths the policy can currently use. Across math, code, and open-ended generation, \shortopd\ raises the compressed model's score to about $9\times$ its unrecovered value and $1.6$–$4.4\times$ standard recovery recipes (SFT w/o KD, KD, and SeqKD), and it matches a fixed $8192$-
token rollout horizon within two points using a quarter of the training time ($8.5$ vs.\ $35.9$ hours) and $71\%$ fewer rollout
tokens. We hope this recipe helps move structured
pruning beyond marginal gains on perplexity and multiple-choice
benchmarks, a step closer to deployment-ready generation quality.
Read the full abstract ▾
All authors Qingyu Zhang, Qianhao Yuan, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun, Ming Xu, Jiarui Li
Artificial Intelligence · Cross-listed from cs.CR
AI in Cyberpsychology: A systematic literature review of Cybersecurity enhancement by using AI for analyzing psychology of Victims, Attackers, and Defenders
Georg Thamer Francis, Malek Malkawi, Sevim Eyüpoğlu et al. (+2 more)
Cybersecurity is the practice of protecting systems, networks, and data from digital attacks. Cyberpsychology (CPSY) is defined as the use of psychology to enhance cybersecurity applications. Since the early 2010s, the
evolution of Artificial Intelligence (AI) has increasingly integrated with CPSY, leveraging advanced data analysis to decode the distinct personality traits and behavioral patterns of victims, attackers, and defenders. In this systematic literature review (SLR), we carefully analyze 34 collected research studies of AI usage in cyberpsychology (AI-CPSY) using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) methodology. The review presents a comprehensive taxonomy of the cyber-security applications, the AI methodologies used, and the psychological concepts employed across the studies . We sort the research studies into four cybersecurity applications: Anomaly Detection (AD), Vulnerability Risk Prediction (VRP), Security Awareness Training (SAT), and Authentication/Identity Verification (AIV). Within each application area, studies are further sorted according to the AI method used including machine learning (ML), deep learning (DL), natural
language processing (NLP), and reinforcement learning (RL). Furthermore, the review identifies the most commonly utilized psychological concepts, quantify the
datasets used in the field, and present their current implementation and deployment status. At last, it detect research gaps, present open challenges, and deduce the trending and most effective and emerging methodologies used across the AI-CPSY landscape.
Read the full abstract ▾
All authors Georg Thamer Francis, Malek Malkawi, Sevim Eyüpoğlu, Reda Alhajj, Selim Akyokuş
Artificial Intelligence · Cross-listed from cs.LG
CoDiffGRN: Rethinking Gene Regulatory Network Inference via the BEELINE-KGC Benchmark and Co-evolutionary Discrete Diffusion
Jiaze Song, Runhao Zhao, Minghao Xu et al. (+2 more)
Inferring gene regulatory networks (GRNs) from single-
cell transcriptomic data is crucial for biological discovery, yet existing approaches suffer from a fundamental misalignment with real-world needs. Researchers typically seek a small set of high-confidence regulatory interactions for experimental validation, often involving previously unseen genes. However, current
benchmarks rely on transductive splits with global classification metrics, while prevailing models struggle to generalize under inductive settings. To bridge this gap, we reformulate GRN inference as an inductive, ranking-centric graph completion problem and introduce \benchmark, a new
benchmark that incorporates an inductive gene-holdout split together with knowledge graph completion metrics to better evaluate top-ranked predictions. Building on this, we propose \method, the first co-evolutionary discrete
diffusion framework that jointly models biologically coherent discretized gene expression states and regulatory interactions for robust inductive generalization and improved top-ranked regulatory discovery. We further introduce TF-ALL Subgraph Sampling (TASS) for scalable training. Extensive experiments on {\benchmark} show that {\method} establishes new state-of-the-art performance, significantly outperforming existing methods in novel regulatory discovery, and ablation studies further verify the effectiveness of our design.
Read the full abstract ▾
All authors Jiaze Song, Runhao Zhao, Minghao Xu, Bin Cui, Wentao Zhang
Artificial Intelligence
Improving Molecular Property Prediction in Small Language Models Using Graph-based Tools
Konstantinos Bougiatiotis, Dimitrios Kelesis and Georgios Paliouras
Small
language models (SLMs) have shown promise for zero-shot molecular property prediction from SMILES strings, yet they often suffer from structural blindness because sequence representations under-specify key graph-topological cues. We propose a modular Context-Augmented Prompting framework that enables agentic tool use at inference time: a trained GNN expert model provides a predictive hint with confidence, and a GNN extracts an instance-specific explanatory subgraph (e.g., a subgraph SMILES and an accompanying explanatory paragraph). We evaluate three commonly used SLMs on MUTAG and Tox21 under five prompting configurations ranging from SMILES-only to using all available tools at hand. Across two
datasets, enriching
prompts with graph-derived context yields substantial accuracy gains, often exceeding 25% relative improvement and up to 74% on Tox21. We further validate the functional relevance of the extracted motifs via a necessity-based edge-drop intervention. Despite the observed gains, a persistent gap remains to specialized GNN models, highlighting both the value and limits of text-conditioned
reasoning for molecular structure.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
SemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests
Maha Ayub, Michael Konstantinou, Ahmed Khanfir et al. (+2 more)
Distinguishing semantic-preserving commits from changing ones remains an open challenge in software repository mining. While existing approaches detect refactoring commits accurately, they cannot ensure that a commit is purely semantic-preserving, without any interleaving behaviour-changing modification. This limitation can impact several tasks, such as debugging, fault localisation, bug
dataset construction, rollback analysis, and bug fixes backporting. To fill this gap, we propose SemaDiff, a novel approach for identifying semantic-preserving commits through behaviour-based analysis; comparison of similar test execution on pre- and post-commit versions. As code impacted by the refactoring is often hard to test and different accross both versions, we propose generating additional calling methods to that code, which serve as testing target. Given a commit, SemaDiff analyses the diff to identify modified code and extracts unchanged dependent code that calls it. It then generates an additional dependent class using a large
language model to exercise the changed code in both versions, and automatically generates tests for the dependent code. This way, we obtain the same tests for the different code versions, enabling the behavioural-difference detection. The commit is classified as semantic-preserving only if all generated tests produce identical outcomes across the two versions. To evaluate SemaDiff, we construct and annotate manually a
dataset of 183 commits, gathered from well-known open-source Java projects. The obtained results show that SemaDiff distinguishes accurately semantic-preserving from – changing commits in about 76% of the cases, with a 100% precision in semantic-changing commit detection.
Read the full abstract ▾
All authors Maha Ayub, Michael Konstantinou, Ahmed Khanfir, Nikolaos Tsantalis, Mike Papadakis
Artificial Intelligence · Cross-listed from cs.LG
A Hybrid Mamba for Audio-Visual Navigation
Yi Wang and Yinfeng Yu
Since the paradigm centered on convolutional neural networks and recurrent architectures was established in 2020, the fundamental backbone networks for audio-visual
navigation have undergone no essential changes for more than five years, making them inadequate to support efficient representation of dynamic
multimodal sequences. This paper proposes Samba(A Hybrid Mamba for Audio-Visual
Navigation). It uses the adaptive selection-enabled Mamba State Encoder (M-SE) to replace conventional GRUs for temporal aggregation, and constructs an Audio Mamba Encoder (AME) to remedy the limitations of convolutional operators in capturing global time-frequency dependencies in spectrograms. Experiments demonstrate that Samba exhibits exceptional generalization performance when facing unheard sound sources and unseen scenes. On the Matterport3D
dataset, it improves the
navigation success rate (SR) by 11.3% compared with existing state-of-the-art models, and the performance gain is even more pronounced on the Replica
dataset, which features finer scene structures. Such modernized architectural reconstruction unlocks stronger
embodied representation capabilities at a lower computational cost, thereby providing a highly robust technical pathway for paradigm
evolution in the field of audio-visual
navigation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting
Sicong Lai, Yuehong Hu, Siru Zhong et al. (+3 more)
Real-world traffic data exhibit heterogeneous spatial correlations and nonlinear temporal dynamics, posing substantial challenges for accurate spatio-temporal
forecasting. Existing approaches have developed increasingly sophisticated graph,
attention, and decomposition architectures, while the influence of the underlying nonlinear function approximator has received comparatively less
attention. In this work, we propose STKAN, a spatio-temporal
forecasting architecture that introduces Taylor-
polynomial Kolmogorov–Arnold Network modules into spatial and temporal
token mixing. STKAN first constructs high-level spatial representations through a learnable soft node-group assignment mechanism, applies group-wise spatial mixing, and subsequently models temporal dependencies over the compressed sequence. Spatial and temporal self-
attention layers are further employed to capture long-range interactions. Experiments on five traffic
forecasting benchmarks show that STKAN achieves competitive performance and performs better than the evaluated MLP-based variant in the tested settings. These results suggest that the design of nonlinear function approximators can serve as a useful complement to architectural design in spatio-temporal
forecasting.
Read the full abstract ▾
All authors Sicong Lai, Yuehong Hu, Siru Zhong, Si Qiao, Yuxuan Liang, Guangyin Jin
Artificial Intelligence
Self-Improvements in Modern Agentic Systems: A Survey
Zhe Ren, Yimeng Chen, Dandan Guo et al. (+9 more)
Self-improving autonomous
agents are moving from research prototypes to deployed systems. The primary goal is controllable
evolution, or adaptation, from experience with minimal or even no human input. This survey frames modern self-improving
agents as adaptive systems that convert experience into accumulated capability gains. We offer a system-level framework that represents a modern
agent as a configuration coupling a foundation model with an operational scaffold of
prompts,
memory, tools, and control logic. Within this framework, self-improvement is formalized as a self-induced update operator that obtains and commits updates to model parameters or scaffold components. We organize prior work by update target and by the signals that drive change, then review applications and discuss evaluation, before closing with open problems and future directions. For convenience, we track technical updates on https://github.com/selfimproving-
agent/awesome-Self-Improving-
Agents.
Read the full abstract ▾
All authors Zhe Ren, Yimeng Chen, Dandan Guo, Guowei Rong, Tonghui Li, R. B. Xiong, Qingfeng Lan, Wenyi Wang, Li Nanbo, Yibo Yang, Mingchen Zhuge, Jürgen Schmidhuber
Artificial Intelligence · Cross-listed from cs.LG
Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing
Duantengchuan Li, Yingqian Bi, Jinsong Chen et al. (+2 more)
Knowledge tracing (KT) aims to predict students' future performance by modeling their evolving knowledge states from historical interactions. Existing KT methods usually treat the raw interaction sequence as a unified behavioral process, overlooking the phase-specific nature of learning behaviors. Our preliminary observations show that students are more likely to correctly answer previously failed knowledge concepts after sufficient practice, suggesting a transition from ability-building to proficiency-oriented learning. Motivated by this, we propose Phase-Aware Knowledge Tracing (PAKT), a KT framework that decomposes student interactions into ability and proficiency phases based on the tailored decomposition mechanism. To effectively exploit the decomposed sequences, we design a multi-branch
Transformer with a type-aware readout module to jointly capture phase-specific and holistic knowledge states. We further provide a causal analysis to reveal the confounding bias caused by entangling complex learning behaviors in phase-agnostic KT models. Extensive experiments on six public
benchmarks demonstrate that our method consistently outperforms representative baselines, with a maximum AUC gain of 1.33% and an average gain of 0.82%.
Read the full abstract ▾
All authors Duantengchuan Li, Yingqian Bi, Jinsong Chen, Rui Zhang, Mingwen Tong
Artificial Intelligence · Cross-listed from cs.LG
TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling
Songru Yang, Zili Liu, Tao Han et al. (+7 more)
Global Station Weather
Forecasting (GSWF) is pivotal for localized and extreme weather prediction over key regions. Despite efforts to exploit look-back windows, existing methods show limited accuracy gains and struggle with extreme events and error accumulation. These limitations stem from overreliance on short-term patterns, which are insufficient to capture chaotic weather dynamics, especially under partial observations. To address this problem, we propose a novel Triaxial State Space Model (TSSM) with a history-enhanced Temporal-VariableHistorical paradigm, which incorporates period-aligned historical weather data to compensate for long-term, large-scale periodic, and full-window weather patterns beyond the temporal lookback window. Specifically, TSSM stacks historical samples into period-aligned batches, where
forecasting is causally supported by historical and current observations. Temporal, variable, and historical scanning are designed to capture axial temporal dependencies, variable correlations, and historical
evolution. This structure is hierarchically shared to model seasonal to extreme events while alleviating misalignment across historical patterns. TSSM achieves SOTA performance on Weather-5K, the largest station weather
dataset to date, with 10% and 61% gains in accuracy and extreme event metrics, and obtains 95% best or second-best results on human-involved
datasets. Its advantages are more pronounced in long-horizon and iterative
forecasting, reaching a 37.5% gain at 240h and up to 103.5% under a 48h times 5 iterative setting. Moreover, TSSM retains > 90% performance under up to 80% missing observations, compared with < 43% for baselines, demonstrating robustness and practical potential for reliable GSWF in global in-situ observation networks.
Read the full abstract ▾
All authors Songru Yang, Zili Liu, Tao Han, Ben Fei, Fenghua Ling, Lei Bai, Chang Liu, Xiangyang Ji, Zhenwei Shi, Zhengxia Zou
Artificial Intelligence · Cross-listed from cs.CR
WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency
Z Sun, Q Jiang, S Sheng et al. (+1 more)
Large
language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques. However, these techniques have rarely been adopted in practice mainly for two reasons: i) severely degraded model performance, and ii) additional inference overhead. To confirm the problem, we construct a comprehensive
benchmark spanning different generation tasks to systematically evaluate 9 representative watermarking methods. We found almost all existing methods are designed for text fluency, but not for restricted and complicated tasks, and their overhead prevents them from deployment in latency-critical systems. To address i) and ii), we propose an LLM watermarking scheme WaterMoE for the growingly popular Mixture-of-Experts (MoE) LLMs. WaterMoE embeds watermarking signals through controlled perturbation into the expert selection at each router, which accumulates to
token selection shift at the final output. In contrast to watermarking as a post-processing
token-sampling approach, WaterMoE embeds watermark within the inference loop incurring negligible quality degradation and computational overhead. Extensive experiments demonstrate that our method achieves a fidelity performance close to the unwatermarked and consistently outperforms state-of-the-art watermarking methods on the
benchmark, with up to $4\times$ speedup, incurring merely 1% additional inference latency compared to native generation. The results demonstrate the capability of WaterMoE to be deployed in real-world tasks.
Read the full abstract ▾
All authors Z Sun, Q Jiang, S Sheng, L Xiang
Artificial Intelligence · Cross-listed from cs.AR
Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit
Xiaomi MiMo Team: Anqi Liu, Aoxin Ma, Bo Chen et al. (+27 more)
We present a full-pipeline inference optimization for the
MiMo-V2.5 model family, which combines Hybrid Sliding Window
Attention (Hybrid SWA), sparse Mixture-of-Experts (MoE), and
multimodal encoders. While Hybrid SWA can ideally reduce both
attention compute and KVCache storage significantly compared to Full
Attention, realizing these gains in production requires substantial engineering effort. We systematically optimize the KVCache system with layerwise prefetch, SWA-aware prefix cache trees, and specialized placement strategies, achieving strict $O(W)$ SWA storage and high cache hit rates. We further build GCache, a high-performance distributed cache infrastructure with RDMA-optimized networking, and develop a KVCache-affinity router to reduce computation while preserving load balancing. We also optimize for
multimodal inputs, including GPU image preprocessing, parallel
video decoding, and
multimodal cache sharing. Together, these optimizations constitute the first large-scale LLM serving system in production that efficiently covers the Hybrid SWA + MoE +
multimodal composite architecture.
Read the full abstract ▾
All authors Xiaomi MiMo Team: Anqi Liu, Aoxin Ma, Bo Chen, Bo Yang, Chen Wang, Chen Zhang, Chengda Tang, Chengwei Wang, Chiheng Lou, Depeng Yan, Fuli Luo, Gang Wang, Hailin Zhang, Jiale Sun, Kang Zhou, Rui Huang, Shaohui Liu, Shen Huang, Shijie Cao, Shuaishuai Fan, Tianling Zhou, Xiangwei Deng, Xueyang Xie, Xuli Wang, Yingchun Lai, Yu Yang, Yuan Zhang, Zhen Tang, Zhonghua Deng, Zihan Jiang
Artificial Intelligence · Cross-listed from cs.CY
Analyzing Curricular Pattern Complexity Using AI to Improve On-Time Graduation Rates
Lynn Vonderhaar, Juan Couder, Siri Siqveland et al. (+2 more)
The rise of Artificial Intelligence (AI) enables automatic analysis of large amounts of data. Previously time-consuming and labor-intensive tasks can be completed much more efficiently with the use of AI. This work uses AI techniques to analyze and revise curricular patterns in an undergraduate degree for Software Engineering. Curricula often have long sequences where failure to pass a class within the sequence may jeopardize completion of the degree within four years. Manual analysis and revision of curricula by university faculty is a lengthy and labor-intensive process, causing changes to occur rarely and making it impossible to keep up with the changing needs of students. This work reduces the time-to-change for curricula and reduces bottlenecks and graduation delays by using Large
Language Models (LLMs) to analyze curricular patterns and suggest revisions.
Read the full abstract ▾
All authors Lynn Vonderhaar, Juan Couder, Siri Siqveland, Omar Ochoa, James Pembridge
Artificial Intelligence · Cross-listed from cs.CR
Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models
Cheng Li, Jiexiong Liu, Yixuan Chen et al. (+1 more)
On-device LLM inference faces a trilemma of response latency, limited hardware resources and user
privacy. Full cloud inference delivers strong computing power but exposes user
prompts and dialogue data, while standalone on-device inference is unfeasible for most consumer and embedded edge devices. This paper presents a
privacy-centric edge-cloud collaborative LLM inference framework built on endpoint-authenticated KV cache. Local endpoints handle input preprocessing,
embedding computation, adaptive feature optimization, KV cache authentication, speculative decoding and low-dimensional model head calculation, while the cloud conducts authenticated decoder inference, KV cache management,
token verification and high-dimensional vocabulary projection. Endpoints fuse partial outputs, apply
language-adaptive masking and sample target
tokens. All transmitted data and truncated logits are quantized and AES-GCM encrypted for
privacy, with core lightweight modules, draft parameters and cache access policies kept local to avoid leakage. The framework supports heterogeneous devices including CPU-only, GPU-equipped and embedded devices via optimized streaming, batching and quantized ONNX deployment. Evaluations demonstrate that the framework reduces per-
token latency by up to 46.1% and downlink payloads by up to 67.4% over baseline split inference, retaining comparable performance to full cloud inference.
Read the full abstract ▾
All authors Cheng Li, Jiexiong Liu, Yixuan Chen, Yi Li
Artificial Intelligence
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
Junjie Yin and Xinyu Feng
Large
language model (LLM)
agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires. They often follow a maximum-context-first strategy–re-reading files and dependencies they have already seen–turning a one-line edit into a small code-base audit. We argue the missing capability is task-aware execution-scope estimation: judging a task's difficulty, the information it truly needs, and the shortest reliable path before committing budget. We formalize minimum-sufficient execution and the
Agent Cognitive Redundancy Ratio (ACRR), and propose E3 (Estimate, Execute, Expand): the
agent estimates an initial operating point, executes a minimum viable path, and expands scope only when verification fails. On MSE-Bench–a deterministic
benchmark of 121 edits in a capability-controlled simulator–E3 matches the strongest baseline's 100% success while cutting cost by 85%,
tokens by 91%, and inspected files by 92%, and further beats a strong adaptive
retrieval baseline by 16%; the gains survive held-out instruction wording and essentially every cost weighting. A companion real-model harness (LLM-Case) corroborates the effect on a live gpt-4o
agent editing a real open-source library, with every candidate patch graded by actually running the project's real pytest suite against a measured oracle: the over-reading is milder but real, and E3 is the leanest and fastest policy at comparable task success–its one shortfall a provider rate-limit, not a wrong edit. We frame this as a controlled probe of execution redundancy, not a measurement of any deployed
agent, and position task-aware execution as a step toward engineering-grounded AI (EGAI)–
agents whose effort is anchored in the engineering reality of the task. We release the framework and
benchmark.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
Zhouchonghao Wu, Akshay Rangesh, Weixin Li et al. (+5 more)
Training robust autonomous driving
agents requires a simulator fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long tail that logged data rarely contains. We present TerraZero, a procedural driving simulator and self-play training stack that meets these goals. A configurable C engine runs simulation on the CPU and policy inference on the GPU over a zero-copy path, sustaining 1.3M
agent-steps per second on a single server-grade GPU, far faster than existing object-level simulators, while keeping fidelity lighter single-
agent systems omit: heterogeneous
agents, multiple dynamics models, and full traffic-rule enforcement. TerraZero uses logged data only as a source of real-world map geometry, populating each map with randomized rule-based road users and signal controllers and randomizing
agent dynamics, rewards, and sizes per episode, so one map yields an effectively unbounded set of scenarios. Every reported policy trains from scratch by reinforcement learning alone, with zero human demonstrations, no imitation, no logged trajectories, and no fallback planner at inference, on a compute-efficient self-play recipe scaled across GPUs. The policies generalize zero-shot across cities and
datasets, including emergent left-hand-traffic driving without explicit supervision. As an ego policy, a single checkpoint is, to our knowledge, the first fully learned policy to top both val14 and the interactive long-tail InterPlan suite. On Waymo Open Sim
Agents realism the same recipe outperforms other demonstration-free methods and is competitive with the strongest reference-anchored self-play method. One stack serves both roles: state-of-the-art demonstration-free driving policies across dynamics for cars and trucks, and sim
agents that jointly control vehicles, pedestrians, and cyclists.
Read the full abstract ▾
All authors Zhouchonghao Wu, Akshay Rangesh, Weixin Li, Wei-Jer Chang, Zachary Lee, Saeed Bonab, Tim Wang, Wei Zhan
Artificial Intelligence · Cross-listed from cs.CL
PalmClaw: A Native On-Device Agent Framework for Mobile Phones
Hongru Cai, Yongqi Li, Ran Wei et al. (+1 more)
Large
Language Model (LLM)
agents have moved beyond generating responses to executing multi-step tasks by calling tools, observing the results, and iteratively deciding the next action. Most
agent systems run on desktops or servers, which support tool use and task automation. Mobile devices are also important
agent environments because they are widely accessible and contain users' data, sensors, and daily-use applications. Existing mobile
agents mainly operate smartphones through graphical user interface (GUI) actions such as tapping, swiping, and typing, which often form long, interface-dependent sequences, cannot directly access device capabilities, and make execution boundaries difficult to define. We present PalmClaw, an open-source
agent framework that runs natively on mobile phones and manages the sessions,
memory, skills, tools, and
agent loop directly on the device. PalmClaw exposes device capabilities as device tools with explicit arguments, structured results, and clearly defined execution boundaries. This design enables
agents to use mobile capabilities directly while keeping each action explicit and controlled. Experiments show an 11.5% relative improvement in task success and a 94.9% reduction in completion time over the strongest baseline, with lower setup burden and traces illustrating how execution boundaries are applied. Code is available at https://github.com/ModalityDance/PalmClaw.
Read the full abstract ▾
All authors Hongru Cai, Yongqi Li, Ran Wei, Wenjie Li
Artificial Intelligence
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
Harsha Vardhan Khurdula, Abhinav Kumar Singh, Yoeven D Khemlani et al. (+1 more)
Automatic
speech recognition is dominated by autoregressive decoders that emit one
token at a time. We ask whether a discrete
diffusion language model can transcribe
speech instead, refining a whole transcript in parallel over a small number of denoising steps. We train an audio-native interface for DiffusionGemma, a 26B mixture-of-experts model that generates text by uniform, random-
token discrete
diffusion rather than the absorbing-mask scheme common to recent
diffusion language models. A frozen Whisper encoder supplies acoustic features, a lightweight projector maps them into the model
embedding space, and low-rank adapters let the frozen backbone attend to the new modality. About 42M parameters are trained, which is 0.16 percent of the backbone. We find that the natural training objectives fail to ground the audio because their gradient reaches the projector only through
attention that has already dismissed it. A connectionist temporal classification loss applied through the frozen output head breaks this deadlock. The resulting model reaches 6.6 percent word error rate on LibriSpeech test-clean, transcribes in roughly eight parallel steps regardless of utterance length, and uses a single adapter trained on six
languages, which we evaluate here on English, Hindi, and Mandarin.
Read the full abstract ▾
All authors Harsha Vardhan Khurdula, Abhinav Kumar Singh, Yoeven D Khemlani, Vineet Agarwal
Artificial Intelligence
Dynamic Resource Allocation for Ensemble Determinization MCTS
Jakub Kowalski, Adam Ciężkowski, Artur Krzyżyński et al. (+1 more)
Simulation-based
algorithms are especially suited for high-uncertainty environments such as
adversarial board games with significant elements of randomness and hidden information. In particular, several Monte Carlo Tree Search (MCTS) variants are commonly used in such domains. In this paper, we propose a series of enhancements for Ensemble Determinization MCTS, introducing two axes for dynamic resource allocation. First, Dynamic Number of Determinizations, increases or decreases the number of currently used determinization trees depending on the behavior of so-far search. Second, Dynamic Simulation Allocation, splits the simulation budget nonuniformly across the determinization trees, using simulation-to-simulation decisions to choose the tree with potentially the best knowledge gain. As
benchmark domains, we used three popular tabletop games: Jaipur, Lost Cities, and Splendor. Testing our proposed enhancements in iteration- and time-based settings showed that particular configurations yield a statistically significant increase in the
algorithm's strength.
Read the full abstract ▾
All authors Jakub Kowalski, Adam Ciężkowski, Artur Krzyżyński, Mark H. M. Winands
Artificial Intelligence
Win by Silence: Deletion Non-Monotonicity, Autonomous Exploitation, and Typed-State Gating in LLM Plan Evaluation
Aleh Manchuliantsau
Plan evaluators can reward a strategic plan for becoming less explicit. This paper studies that failure in a staged expected-value scorer for LLM-generated venture routes. Proposition 1 gives the score change from deleting an interior transition while retargeting its predecessor and retaining downstream value: Delta_k = (prod_{i<k} p_i)[c_k + (1 - p_k)R_{k+1}]. On a frozen 26-route cohort, all 57 admissible deletions matched the analytic identity and threshold sign, and every route had at least one score-improving deletion. A score-seeking optimizer, allowed to restructure routes but not told the exploit mechanism, found baseline-beating uncovered structures in 21/26 routes. GATE refused score release for 26/26 silenced routes with 0/26 honest suspensions; after refusal, 47/54 next revisions repaired to a covered structure, and strict covered improvement rose from 1/26 to 13/26. An adaptive compiler-aware co-author exposed the registry-provenance boundary: obligation-channel evasions remained 6/6 across all four v1/v1.5 conditions, while delta-indexed cost floors reduced beat-honest routes from 6/6 to 3/6 and fundability-by-silence from 5/6 to 0/6 without establishing semantic completeness. If a plan scores better only because it omits necessary work, the plan did not improve; the evaluation created an omission incentive. PCSC detects and neutralizes post-hoc omission splices over model-mediated typed-state records. In the cooperative setting tested, GATE acts as a deterministic search-shaping constraint, not merely a post-hoc filter. It does not verify the semantic completeness or real-world quality of arbitrary LLM-generated strategies.
Read the full abstract ▾
Artificial Intelligence
Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
Sen Yang and Yuen-Hei Yeung
Aligned
language models routinely misreport under non-evidential pressure: they cave to a confident user, yet fail to revise when genuine evidence arrives. We cast this as a failure of internal incentive-compatibility and study the two demands, resist (ignore forbidden pressure) and update (follow licensed evidence), on a
Bayesian-witness
benchmark with known posteriors, where the same user disagreement is evidence or pressure purely by stated source reliability, removing the evidence/pressure confound by construction. Using interchange interventions rather than probes, we causally localize low-rank report coordinates for answer, confidence, and caveat, establishing causal sufficiency at a late intervention site rather than uniqueness or necessity, with a causal cross-talk
matrix showing strong own-coordinate control and only small cross-effects (partial functional disentanglement). We then introduce a training-free counterfactual report-coordinate (CRC) clamp that references the model's own report under an incentive-neutralized counterfactual of the
prompt. The two-pass full-window clamp attains resist and update of $1.00$ jointly (Wilson 95% CI $[0.99,1.00]$; the rank-16 projection alone reaches $0.88/0.90$), which we read as a causal certificate and upper bound under a constructible reference, not a claim of a deployed solution. Tested global decoding and fixed-direction steering trade one objective against the other, and resist-only training collapses updating to $0.01$. The deployable single-pass compilation is lossy ($0.73/0.97$). The mechanism and the clamp reproduce across three model families and transfer to a natural sycophancy
benchmark with significant paired improvements. Our contribution is the interface and certification method: activation-level counterfactual incentive-invariance as a structural primitive for internal incentive-compatibility.
Read the full abstract ▾
Artificial Intelligence
FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation
Ruoran Xu, Wending Gao, Xiaoqing Kang et al. (+1 more)
Math
reasoning has achieved significant progress with the rapid advancement of
Multimodal Large
Language Models (MLLMs), however analytic geometry remains largely underexplored, primarily due to the scarcity of annotated samples. Existing diagram generation approaches struggle with analytic geometry: template methods cannot handle constraint-driven layouts, and generative models lack the
geometric precision to render annotated conic curves correctly. We present FormalAnalyticGeo, a scalable framework for fully automatic generation of
multimodal analytic geometry problems. Leveraging the rigor of formal
languages, we design the framework around CDL (Condition Description
Language), a formal intermediate representation that bridges free-form problem text with precise diagram rendering via a Signed Distance Field (SDF) engine. The framework employs four specialized LLM components in sequence: a Generator that produces diverse analytic geometry problems, a Formalizer that converts each problem into CDL for SDF-based rendering, a Measurer that extracts ground-truth answers through
vision-based measurement on the rendered diagrams, and a Quality Verifier that checks outputs at three stages. Structured feedback from the Quality Verifier drives automatic retry, forming a closed loop that eliminates any need for human annotation. Applying FormalAnalyticGeo at scale yields AnalyticGeo7K, a
dataset of over 7K verified
multimodal problems, each with aligned text, diagram, formal annotation, and ground truth.Experiments show that the generated problems achieve a median ground-truth relative error of 0.70%, with 82.3% of answers falling within 5% of the exact symbolic solution. Our framework and
dataset will be publicly released.
Read the full abstract ▾
All authors Ruoran Xu, Wending Gao, Xiaoqing Kang, Qiufeng Wang
Artificial Intelligence · Cross-listed from cs.SE
Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models
Mehmet Iscan
Frozen small code LLMs are deployed locally, yet the information guiding a retry after a failed attempt is still measured without placebo controls in the self-repair literature. We treat a failed program as a
conjecture and an execution counterexample as an oracle-relative refutation, and introduce PoPE (Popperian Placebo-controlled Evaluation): a methodology for measuring whether evidence that falsifies LLM-generated code can be used operationally by that same model. In PoPE, error content is paired with channel-specific placebos that keep the predeclared scaffold while ablating task-relevant content or deranging the task-error assignment. Frozen small code models (0.5-1.5B) are evaluated under preregistered rules through a
prompt channel and a weight channel (small-data adapter training), with four generations per arm-unit pair. In the
prompt channel, public-tier screening unlocked 12 units under the content-ablated form placebo versus 10 under the live error-pattern arm on a 40-unit resistant band; the result was recorded as mechanism-null. In the weight channel, an 8-8 tie was observed between the error-content adapter and the intervention-free baseline (p=1.0), while the SHA-deranged placebo adapter stayed ahead with 10 unlocks; content-attributable superiority was not confirmed. These results do not constitute evidence of equivalence or non-inferiority. Equivalence was not tested separately. Findings are restricted to the public-tier screening endpoint; hidden-tier confirmation was deferred by design. We read this not as compiled criticism disappearing as information, but as the loss of its external role in testing a new
conjecture: when a representation learned from the oracle is written back into the generation state, testing is replaced by conditioning. No working JEPA-RL controller is claimed. PoPE is presented as a placebo-controlled, retestable measurement standard.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
ViHoRec: A Quality-Controlled Vietnamese Hotel Recommendation Dataset and Cold-Start Benchmark
Minh Hoang Nguyen
Recommender-system research for Vietnamese remains limited by the absence of a public, well-documented hotel interaction resource. Building such a resource is challenging for three reasons: cross-platform hotel names must be reconciled before interactions are comparable; quality must be audited with reproducible metrics rather than ad hoc cleaning; and public release must preserve
privacy while remaining benchmarkable under realistic cold-start conditions. We introduce ViHoRec, a quality-controlled Vietnamese hotel recommendation
dataset of 18{,}267 interactions between 6{,}832 users and 560 hotels, crawled from Booking.com, Traveloka, and Ivivu. Our contributions are: (i) a reproducible construction pipeline with cross-platform entity resolution and quantitative quality control; (ii) a
privacy-preserving release with HMAC pseudonyms; and (iii) a public cold-start
benchmark with temporal leave-last-one-out split, data-centric ablations, and dependency-free baselines. On the public split, learned models degrade sharply for users with short histories (BPR-MF Recall@10: 0.065 vs. 0.120), while UserKNN remains strongest overall, establishing ViHoRec as a sparse, cold-start-dominated testbed for low-resource recommendation. All data are publicly available at https://github.com/MinhNguyenDS/ViHoRec.
Read the full abstract ▾
Artificial Intelligence
Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes
Jonas Ehrhardt, René Heesch and Oliver Niggemann
In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters. In such settings Reinforcement Learning
algorithms typically determine parameters with one-shot
estimators, which makes their training sample inefficient. Though in most PAMDP environments explicit but incomplete knowledge (e.g., rules, safety constraints, or expert heuristics) is available, it is rarely directly used to increase the sample-efficiency of training Reinforcement Learning
agents. We step into this gap and propose our novel Neuro-Symbolic Knowledge- and Gradient-Guided Reinforcement Learning (KGRL)
algorithm. KGRL uses domain knowledge in a Datalog knowledge base to derive the set of applicable actions and feasible parameters for a given state. This allows it to prune non-applicable actions from the decision-space and constrain the parameter spaces of the remaining actions. We then use a gradient-based parameter refinement loop to estimate the optimal parameters during training and deployment of the
agent. By recording activated rules along the trajectory, KGRL additionally provides local procedural explanations on the
pruning of actions and constraining of parameters. Overall, KGRL guides the
agent's exploration and deployment toward feasible and constraint-aware decisions, while increasing sample efficiency during training. KGRL outperforms state-of-the-art RL baselines for PAMDPs in both, sample efficiency and episodic return.
Read the full abstract ▾