Artificial Intelligence · Cross-listed from cs.CL
TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability
Vincent Cohen-Addad, Dimitris Paparas, Ernest van Wijland et al. (+13 more)
We introduce TCS-Bench, a
benchmark for evaluating Large
Language Models (LLMs) on research-level Theoretical Computer Science (TCS) proof generation. TCS-Bench consists of
theorem-proving tasks from papers published at top theoretical computer science venues (STOC, FOCS, and SODA). Each task provides the necessary context to derive a self-contained proof for a target result. We evaluate state-of-the-art models on this
benchmark. We verify the correctness of generated proofs via a verification
agent, and further
benchmark the verifier against human-expert proof judgements on a set of target statements and generated proofs pairs. Our reference verifier achieves over 90% accuracy on the expert labeled set.
Read the full abstract ▾
All authors Vincent Cohen-Addad, Dimitris Paparas, Ernest van Wijland, Max Springer, Julien Canitrot-Paradis, Honghao Lin, David Woodruff, Adarsh Kumarappan, Rajesh Jayaram, Rudrajit Das, Lalit Jain, Ola Svensson, Silvio Lattanzi, Mislav Balunovic, Theophane Weber, Vahab Mirrokni
Artificial Intelligence
VERDI:Verified Contradictions for Continual World-Model Optimization
Junyu Wu, Shiqin Nie, Youyi Kou et al. (+10 more)
Foundation world models have made remarkable progress in planning, simulation, and
embodied intelligence. However, optimizing a pretrained world model toward a user-specified objective remains difficult: each campaign typically rediscovers optimization strategies from scratch, and the resulting knowledge rarely transfers to the next model. Existing research
agents automate the optimization loop but treat successful strategies as directly reusable recipes, without principled safeguards for when transfer is appropriate. We argue instead that
retrieval is not transfer: a strategy validated on one model is at best an optimization hypothesis for another, and becomes transferable knowledge only after target-side experimental valida- tion. Guided by this principle, we propose VERDI , a continual framework for evidence-licensed world model optimization. VERDI characterizes each world model through shared inference-time probes to construct an Optimization Fin- gerprint, retrieves relevant prior experience as ranked hypotheses, and validates every candidate under a frozen target-side verifier before admitting it as reusable evidence; contradictions among nearby fingerprints further trigger probe
evolution, continually refining the diagnostic representation itself. Experiments on Ctrl-World, the Cosmos family, and RoboCoin show that VERDI reduces search cost by 68%, GPU cost by 69%, and negative transfer from 0.34 to 0.06, while predicting transfer outcomes with 83% sign accuracy.
Read the full abstract ▾
All authors Junyu Wu, Shiqin Nie, Youyi Kou, Baohua Yin, Qingyu Chen, Jingheng Ma, Shiji Zhou, Hongyong Song, Mingchen Zhuge, Guocai Yao, Tielin Shi, Sen Cui, Changshui Zhang
Artificial Intelligence · Cross-listed from cs.DB
Carnot: Interpretable, Interactive, and Optimized Execution of Deep Research Queries
Matthew Russo, Yash Agarwal, Tianyu Li et al. (+5 more)
Enterprises increasingly seek to query data lakes using natural
language via AI-driven tools like semantic operators or deep research
agents. However, the latter operates as an opaque black box, hiding its intermediate
reasoning and data
retrieval steps, and failing to expose controls for managing API costs and execution latency. Meanwhile, the former can be prohibitively expensive for enterprise-scale data lakes. Consequently, analysts using these systems lack the agency to intercept hallucinated premises, verify intermediate results, or correct the system's trajectory. We present Carnot, an interactive execution engine for AI-driven analytics. Carnot compiles natural
language requests into physical execution graphs and surfaces them through an interactive notebook interface. Rather than waiting blindly for a final output, users can critique the plan, incrementally execute operators, inspect intermediate data, or directly edit the underlying code or semantic operator instructions. Carnot's query optimizer will optimize the query with respect to cost or latency constraints provided by the user. Our demo will showcase how Carnot helps users achieve efficient and verifiable insights on workloads motivated by real enterprise use cases.
Read the full abstract ▾
All authors Matthew Russo, Yash Agarwal, Tianyu Li, Zhuohan Gu, Michael Cafarella, Omar Khattab, Tim Kraska, Samuel Madden
Artificial Intelligence · Cross-listed from cs.CR
RangeFactory: Scalable Construction of Multi-Hop Cyber Ranges
Hanlin Jiang, Puyi Wang, Jiandong Jin et al. (+10 more)
Real-world cyberattacks often require sustained progress across multiple hosts and network segments, making multi-hop cyber ranges essential infrastructure for studying and improving LLM
agents' ability to sustain complete attack chains. Prior work has scaled isolated vulnerability tasks and constructed multi-host scenarios from manually specified vulnerability semantics. However, they are still unable to automatically orchestrate the growing supply of vulnerability environments into end-to-end validated multi-hop ranges. To this end, we present RangeFactory, an automated cyber-range orchestration framework that constructs multi-hop cyber ranges at scale from isolated vulnerability environments. RangeFactory formulates range construction as dependency resolution: it extracts dependency information from
agents' actual attacks against real vulnerabilities, resolves known dependencies through template-guided orchestration, and uses end-to-end attack execution to validate runtime dependencies that emerge after composition. Using RangeFactory, we construct RangeBench with 1,148 validated range instances spanning 287 distinct attack chains and evaluate frontier attack
agents across attack depth, network scale, and task information. Among runs that compromise the entry vulnerability, 24.5-47.0% still fail to complete the remaining attack path, revealing a substantial sustained-compromise gap between establishing an initial foothold and completing a multi-hop attack. RangeFactory further produces a corpus of 5,541 outcome-annotated multi-hop attack trajectories, providing execution data for attack-process analysis and future
agent training.
Read the full abstract ▾
All authors Hanlin Jiang, Puyi Wang, Jiandong Jin, Shaofei Li, Zhan Shen, Pengli Wang, Ziming Wang, Yifeng Cai, Ning Jia, Yuxin Ren, Peng Jiang, Yao Guo, Ding Li
Artificial Intelligence · Cross-listed from cs.CR
STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework
Hanlin Jiang, Jionghao Huang, Shaofei Li et al. (+6 more)
Incident response planning is critical for restoring compromised software systems. Existing AIOps methods automate fault diagnosis and remediation and adapt response using feedback, but lack a unified decision basis across planning and execution. This limits their ability to maintain incident state and align actions with evolving recovery objectives during long-horizon, multi-stage security incident response. We present STAIR, an end-to-end agentic response framework that organizes planning and execution around a shared incident state. STAIR maintains incident evidence, response actions, and execution feedback in Graph-as-State (GAS), using the latest state to determine the response stage and recovery objectives for stage-specialized planning. The framework retrieves effect-validated historical experience based on the current state and stage to guide action selection. An Execution Harness executes actions, returns feedback to update GAS, and validates action effects for future experience reuse. We construct STAIR-Bench, an executable incident response
benchmark comprising 44 Docker-based cyber-range cases. On its held-out test cases, STAIR achieves an overall defense score of 0.95, improving over the strongest baseline by approximately 10.47%. In the independent CAGE4 environment with ongoing attacks and benign activity, STAIR reduces cumulative penalties by approximately 28.8% relative to the strongest baseline.
Read the full abstract ▾
All authors Hanlin Jiang, Jionghao Huang, Shaofei Li, Bojia Yu, Peng Jiang, Yuxin Ren, Ning Jia, Yao Guo, Ding Li
Artificial Intelligence
One Adapter Pair per Model: A Universal Activation Interface for Language Models
Su-Hyeon Kim, Jiwan Mun and Yo-Sub Han
Activation-based tools are usually tied to one model's native hidden space, requiring probes, sparse autoencoders, and natural-
language interpreters to be rebuilt or rediscovered for each new
language model. We present a Universal Activation Bus, a framework that provides a common activation interface across compatible
language models. Using a small set of source models, we learn a shared dense space together with one lightweight linear encoder–decoder adapter pair per model. After source training, the interface is frozen; a new model joins by fitting only its adapter pair on unlabeled matched text. The resulting interface allows activation-based tools to be shared across connected models, including common probes and SAE features as well as access to an NLA originally trained for a different model. Across five models, semantically related texts form consistent neighborhoods in the shared space, and an onboarded model reuses these tools effectively without retraining them. We further show that an intermediate activation from one model can be used by another model's frozen upper layers to produce predictions. These results establish a stable, model-wise activation contract for reusable tools across compatible
language models.
Read the full abstract ▾
Artificial Intelligence
Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification
Karim Zaghw, Andrew Pashea, Marc Pritsch et al. (+3 more)
Active inference offers a unified framework for perception, learning, and action, but scaling discrete active-inference models to rich spatial and temporal domains remains difficult. Renormalising generative models (RGMs) address this challenge by composing discrete generative models across spatial and temporal scales, coarse-graining lower-level states and paths into higher-level causes for objects, events, and action. However, fully reproducing and adapting the framework remains difficult: the mathematical exposition is compact, and the reference implementations are deeply integrated within specialized software environments, leaving many algorithmic details implicit. This paper addresses these challenges by providing a self-contained, derivation-oriented account of RGMs together with an open, verified implementation. We explain how the hierarchy is built, how beliefs and actions are updated within it, and how information is passed between levels. Where the published equations and implementation differ in emphasis, we make those choices explicit and explain their modelling consequences. By clarifying the theory and separating it from its original implementation context, this work lowers practical barriers to entry and makes RGMs more transparent, auditable, and reproducible, providing a foundation for future quantitative evaluation and development on machine-learning
benchmarks.
Read the full abstract ▾
All authors Karim Zaghw, Andrew Pashea, Marc Pritsch, Wouter Nuijten, Karl Friston, Lancelot Da Costa
Artificial Intelligence · Cross-listed from cs.CL
Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media posts
Kevin Thomas, Milosz Kasprzyk, Reuel C Igbokwe Onuigbo et al. (+5 more)
Detecting machine-generated disinformation on social media is increasingly difficult as large
language models (LLMs) make it easier to generate and rewrite misleading content at scale. Static
benchmark evaluations, measuring detector performance on fixed held-out
datasets, do not capture how detectors behave when posts are deliberately transformed to evade classification. This paper adapts the Build it, Break it, Fix it framework into Build it, Break it, Repeat (BiBiR): iterative sessions designed to stress-test detectors' robustness under iterative
adversarial conditions, evaluating whether models remain reliable when disinformation posts are systematically transformed to evade classification. Across five iterations, the findings show that the best
adversarial breakers' transformations came from a combination of back-translation and LLM persona-based rewriting, with the best performing technique achieving a 95% label flip rate (LFR), whilst still preserving the meaning of the original posts. The best builders' model was a triplet contrastive model with a dynamic anchor switching (DASS) architecture, which achieved an average accuracy of 72.68%, outperforming the strong baseline (a fine-tuned e5-small-LoRA) by 15 percentage points on the most robust set of breakers'
adversarial attacks. The results demonstrate that an iterative framework best exposes detector weaknesses and pushes robustness improvements; however, it may still require semantic preservation analysis to distinguish valid
adversarial evasion from transformations that changed the original disinformation claims' meaning.
Read the full abstract ▾
All authors Kevin Thomas, Milosz Kasprzyk, Reuel C Igbokwe Onuigbo, Elliott Pert, Cameron Tovey, João A. Leite, Olesya Razuvayevskaya, Carolina Scarton
Artificial Intelligence · Cross-listed from cs.CL
Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning
Yuting Liu, Wei Wu, Jianzhe Zhao et al. (+1 more)
Natural
language user preferences provide an interpretable interface for LLM personalization. However, universal preference summaries often contain information irrelevant to a particular downstream task. Directly supplying the full preference summary therefore wastes context capacity and introduces cross-task distraction, while manually designing task-specific preference views is difficult to scale. In this work, we study task-specific preference adaptation: given a universal user preference summary and a downstream task, derive a task-conditioned representation that preserves sufficient decision-relevant evidence while removing redundant context. To this end, we propose AlignXada, a training-free meta-learning framework that induces reusable textual refinement policies for adapting universal preference summaries to task-specific ones. The refinement policy is iteratively optimized by a meta learner through verbal reinforcement learning. Across 13 tasks and three downstream models (39 task–model
cells), AlignXada achieves an average gain of 3.82 points, improving 33
cells while retaining only 22.8% of the original profile
tokens and outperforming RAG in 36
cells. An extended faithfulness analysis further shows that the refined profiles remain largely grounded in the source preferences while preserving task-relevant personalization signals, suggesting that profile-side adaptation serves as a practical complement to universal
memory construction for lifelong personalized
agents.
Read the full abstract ▾
All authors Yuting Liu, Wei Wu, Jianzhe Zhao, Guibing Guo
Artificial Intelligence
Capability Is Not Propensity: Measuring Pressure-Robust Cooperative Behavior in Civic LLM Agents
Neel Tushar Shah, Manglam Kartik and Akshat Karkar
Cooperative capabilities in
language models are dual-use. The same social
reasoning that supports civic deliberation can also enable strategic omission, false consensus, and manipulative framing. We argue that Cooperative AI evaluations should separate what models can do under benign instructions from what they tend to do under realistic civic pressure. We introduce DiffCoop-Civic, a 10-scenario pilot evaluation suite spanning preference understanding, evidence and persuasion, commitment design, asymmetric information, and dissent preservation. Across seven models from four model families, subtle omission pressure produces a near-uniform shift: manipulative enablement rises by 1.17 points and dissent preservation falls by 1.67 points on a 5-point scale. Overt false-consensus pressure behaves differently: it triggers refusal or redirection in some aligned API models, but direct compliance in several open-weight models. A lightweight Pareto-Trace prompting intervention improves pressure robustness without simply relying on hard refusal. An anonymous reproducibility package is available at https://anonymous.4open.science/r/diffcoop-civil-771C.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Beyond Uniform Restoration: Empowering All-in-One Restoration with Pixel-Level Multimodal Guidance
Chunxiao Liu, Wei Liu, Anbin Xiong et al. (+1 more)
All-in-one image restoration is a unified low-level
vision task that aims to effectively recover high-quality images from inputs degraded by various types and levels of corruption using a single model. Recent works have achieved remarkable progress by learning degradation-adaptive
prompts or network architectures. However, these methods typically apply a uniform restoration strategy across the entire image, neglecting the fact that different regions may suffer from distinct degradation types and varying degrees of severity. In contrast, we propose to perform restoration at the pixel level, thereby enabling more fine-grained and precise control over the restoration process. Specifically, we present MGN-AIR, a novel pixel-level restoration framework for all-in-one image restoration. Our approach first learns to estimate a pixel-level visual
prompt. Then, it leverages both textual and visual
prompts to provide global and local degradation cues, guiding the model on where to look and how to restore at each pixel. We conduct extensive experiments on multiple all-in-one image restoration
benchmarks, covering a wide range of tasks including denoising, deraining, deblurring, dehazing, desnowing, and low-light enhancement. Experimental results demonstrate that our proposed method consistently and significantly outperforms existing approaches.
Read the full abstract ▾
All authors Chunxiao Liu, Wei Liu, Anbin Xiong, Erli Meng
Artificial Intelligence
From Prompt to Harness: Coderlet from Scratch
Mengfan Li
A model alone does not determine how a programming
agent acts. What the model sees, how actions enter the environment, how feedback returns, and how one run affects the next all depend on how the harness is organized. Minimal examples usually show only the basic interaction between a model and tools, while production systems spread these relationships across complex components and dependencies. This paper studies a compact harness design by following a single request through context formation, model decision, environmental action, observation return, and state continuation. Three boundaries—model, execution, and state—connect the model service, tool environment, and persistent state, while the request lifecycle determines the order in which these transitions occur. Together, they show the harness's core role: turning model generations into environmental actions, carrying runtime feedback into later decisions, and allowing state to continue across requests. On top of this runtime structure, a harness can also be gradually refined across runs through continued bootstrapping. The design is realized in the executable artifact https://github.com/lilinxi/Coderlet.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents
Hongwei Yao, Yiming Liu, Meihui Chen et al. (+6 more)
Cowork
agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBench, a self-evolving
benchmark that evaluates such behavior risk from execution trajectories rather than final responses. Each case pairs a benign task with an
adversarial variant that preserves its instruction, configuration, initial state, rating model, and trusted records while injecting a task-reachable payload. ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and 48 web-service APIs.To move beyond static payloads, we propose a reward-guided beam search method that jointly optimizes attack effectiveness and task utility, while reflection diagnoses failed execution checkpoint and guides payload revision. Besides, we propose a dual evidence verification mechanism that verifies
agent execution safety and utility through log evidence and LLM-based trajectory evidence.We evaluate 15 LLMs and 6 open-source cowork
agents over 24,000 trajectories. Under a fixed harness, attack success rates ranges from 10.1% to 94.4% across models, while under a fixed base model, they range from 73.7% to 94.4% across
agents.These results show greater variation across models than
agent harness, while attacks remain highly successful across all tested harnesses.Our
benchmark is released at: https://github.com/zjuicsr/ActBench.
Read the full abstract ▾
All authors Hongwei Yao, Yiming Liu, Meihui Chen, Jieling Chen, Zikun Chen, Yiling He, Wangze Ni, Cong Wang, Kui Ren
Artificial Intelligence · Cross-listed from cs.LG
MixFormer: Linear Transformer with Mixture of Memory Experts
Yu Guo and Lei Duan
State Space Models (SSMs), as a mainstream research direction of linear
Transformers, aim to achieve higher efficiency than standard
Transformers in long-context modeling. However, existing SSMs suffer from limited input adaptivity and constrained
memory capacity, leading to information loss when modeling ultra-long sequences. To address these limitations, we propose MixFormer, a novel linear
Transformer that integrates a Mixture-of-
Memory-Experts (MoE) mechanism. Specifically, the model maintains differentiated
memory states through multiple collaborating
memory experts and employs a novel Time-Aware Linear
Attention (TALA) mechanism, which leverages learnable exponential decay functions and positional biases to dynamically update
memory. This design enables the model to selectively reinforce important historical information while effectively mitigating
memory dilution, substantially improving long-range dependency modeling. Experiments on long-sequence text and image generation tasks demonstrate that MixFormer not only achieves significant performance gains but also provides a more sustainable computational backbone for the next generation of web infrastructure.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
RefineFly: Failure-Aware Post-Training for Aerial Vision-Language Navigation
Boxiong Wang, Hui Kang, Geng Sun et al. (+3 more)
Unmanned aerial vehicle
vision-
language navigation (
UAV-VLN) requires
agents to translate visual observations and
language instructions into reliable flight actions in complex environments. Although recent end-to-end
UAV vision-
language-action (
UAV-VLA) policies reduce reliance on separately designed perception, planning, and control modules, their behavior-cloning objectives provide limited supervision for errors arising during closed-loop execution. Reinforcement learning (RL) offers a promising solution, while limited interaction budgets, long-tailed scene distributions, and policy drift complicate sustained learning. To this end, we propose RefineFly, a failure-aware RL post-training framework for end-to-end
UAV-VLA policies. Built on
token-level proximal policy optimization (PPO), RefineFly maintains dynamic failure
memory within a two-stage scene curriculum to sustain learning from unresolved tasks as training shifts from empirical to balanced scene sampling. Throughout this process, stage-specific reference regularization constrains policy deviation. Experiments on the TravelUAV
benchmark demonstrate that RefineFly outperforms all comparison methods across all three splits, improving success rate over AerialVLA by 3.12 to 8.37 percentage points with a total rollout budget of about 30% of the training-set size. Moreover, ablations reveal that the benefits of sustained failure learning vary across evaluation splits, while the two-stage scene curriculum improves overall performance, highlighting the importance of training distributions when learning from failures.
Read the full abstract ▾
All authors Boxiong Wang, Hui Kang, Geng Sun, Jiahui Li, Chao Yu, Daxin Tian
Artificial Intelligence · Cross-listed from cs.LG
Learning to Modulate, Not to Cycle: Soft Actor—Critic Recovers Inverter-Style Heat-Pump Control
Faizan Ahmed, Aniket Dixit and James Brusey
On–off cycling is the main cause of compressor wear in residential heat pumps, yet reinforcement learning (RL) controllers for buildings typically optimise only energy cost and thermal comfort, ignoring how much the learned policy cycles. We add a levelised compressor-wear term to the control reward and study how the resulting behaviour depends on the RL
algorithm. Training Soft Actor—Critic (SAC) and Proximal Policy Optimisation (PPO) on an identical Markov decision process for the BOPTEST bestest hydronic heat pump case, we find that SAC learns a continuous modulation policy that keeps the compressor permanently engaged—the operating principle of an inverter-driven heat pump—achieving zero start-ups per day, whereas PPO collapses to bang-bang control that cycles more than the baseline. On the BOPTEST emulator the SAC policy cuts thermal discomfort by up to 90.7% for an 11.5% cost increase, while eliminating all baseline cycling.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training
Zehao Chen, Gongxun Li, Tianxiang Ai et al. (+9 more)
On-policy
distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline
distillation. The same feedback loop can nevertheless be unstable: each update changes both the policy and the states on which the next update is computed. We introduce WDL-OPD, a mixture-constrained co-training method with two trainable policies. An anchor policy generates every rollout, an auxiliary policy evaluates the same visited states, and a
geometric mixture of their
token distributions is matched to a frozen teacher by reverse KL. Both policies receive gradient. We show that freezing the auxiliary recovers an anchor-plus-contrast proxy target closely related to OPD$^2$ and W2S-OPD, whereas joint training creates branch-level degrees of freedom that a static delta cannot express. In recorded Qwen3 experiments at 1.7B and 4B scale, WDL-OPD produces the strongest student checkpoint in each of four scale-domain settings. It raises MATH500 accuracy from 0.630 to 0.685 at 4B and from 0.521 to 0.585 at 1.7B. In code generation, seven single-policy OPD configurations exhibit
entropy growth or trajectory degradation, while co-training reaches independently re-evaluated development scores of 0.637 and 0.375. Because several comparisons differ in curriculum or initialization, these results support a stabilization hypothesis rather than a universal causal claim. We provide the exact training
algorithm, failure evidence, and the controlled comparison
matrix needed to test that hypothesis.
Read the full abstract ▾
All authors Zehao Chen, Gongxun Li, Tianxiang Ai, Yifei Li, Zixuan Huang, Wang Zhou, Tao Huang, Fuzhen Zhuang, Xianglong Lu, Jianxin Li, Deqing Wang, Yikun Ban
Artificial Intelligence
Coupled Graph–Policy Distillation for Personalized Medication Safety in Older Adults with Multimorbidity
Zihan Wang, Anglin Liu, Rongyi Wang et al. (+6 more)
Large
language model (LLM)
agents can support medication review between clinical visits, but safe choices for older adults with multimorbidity depend on conditions, medications, and geriatric risks that users may omit. We introduce ATLAS, a coupled graph–policy
distillation framework for patient-adaptive medication safety. ATLAS structures guideline evidence as a medication-safety graph. Targeted questions update the patient state and distill relevant relations into a patient-specific medication conflict graph (PMCG). A risk-first multi-
agent policy uses the PMCG to screen contraindications, assess cautions and monitoring needs, identify safer alternatives, and verify the final medication plan. We also introduce GeriMedBench, an interactive
benchmark that tests safety-critical information acquisition and evidence-based decision revision. Across a European non-interactive multimorbidity
benchmark, an Asian interactive multimorbidity
benchmark, and an Asian non-interactive cross-guideline
benchmark, ATLAS achieves the strongest complete-decision performance among the compared systems. On the European non-interactive multimorbidity
benchmark, it exceeds the strongest proprietary LLM baseline by 53.73 points in Strict Success Rate and 14.63 points in overall safety
reasoning score (OSRS), with no unsafe recommendations under the automated evaluator. A blinded clinician evaluation gives ATLAS higher mean ratings across all five criteria and flags potentially unsafe recommendations in one ATLAS case and two Gemini cases.
Read the full abstract ▾
All authors Zihan Wang, Anglin Liu, Rongyi Wang, Dantong Li, Yi Lu, Siqing Yuan, Hongxia Xu, Zhongtian Long, Jintai Chen
Artificial Intelligence
Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models
Zhi Zeng, Cheng Zhang, Zesheng Yang et al. (+9 more)
Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-
language models often represent clips as global acoustic events, while
vision-
language models lack the spatial audio cues needed to localize and track individual sources. To evaluate this missing capability, we introduce ST-OmniQA, a spatio-temporal audio-visual question-answering
benchmark built from panoramic
videos paired with synchronized first-order Ambisonics (FOA) audio of moving sound sources. It contains 40K
videos and 400K question-answer pairs organized into four capability levels covering sound-event recognition, direction of arrival, source distance, motion trajectories, and temporally grounded audio-visual
reasoning. Building on this
benchmark, we propose ST-Omni-R1, which integrates FOA-derived semantic and trajectory representations with panoramic visual context and is trained through progressive curriculum learning and
reasoning-tree reinforcement learning. ST-Omni-R1 achieves 77.83% average semantic accuracy across the four levels, compared with 37.28% for the best evaluated baseline. Results on three public spatial-audio
benchmarks further indicate that its learned spatial and motion representations transfer beyond ST-OmniQA.
Read the full abstract ▾
All authors Zhi Zeng, Cheng Zhang, Zesheng Yang, Rendong Pi, Jiaying Wu, Di Zhang, Zihan Ma, Guodong Li, Zhou Yang, Yu Xiang, Yifei Zheng, Minnan Luo
Artificial Intelligence · Cross-listed from cs.LG
How Simple Can It Get? From Interpretable Equations to Readable Rules for Financial Decision Making
Adia Lumadjeng, Ilker Birbil and Erman Acar
In regulated domains such as finance, a model that cannot be explained cannot be deployed, yet many interpretable classifiers defeat their own purpose by producing formulas with dozens of features that no regulator could read. We take the reverse direction. Starting from an interpretable classifier expressed as a single equation over the input features, we progressively simplify it into more readable forms, including a pruned monomial, a directional if–then rule, and the integer scorecards and tallies that finance already deploys. Because the equation is itself the predictive model rather than a post-hoc explanation we can directly quantify what is lost under each simplification. Across four financial
datasets, we find that
pruning is nearly free and that fidelity can erode faster than predictive performance, allowing simpler rules to remain effective classifiers without faithfully reproducing the original model. A human assessment shows that simplification improves perceived readability, while preferences for different representations vary by professional background. Beyond measuring these losses empirically, we show that some can be anticipated from the original model: we derive a bound on the change caused by
pruning and predict how faithfully a rule retaining only the direction of each feature's effect preserves the original ranking.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
ZetaGPT: A Reference Implementation of Positional–Encoding–Free State–Space–Attention Language Models
Róisín Luo
Transformer-based
language models rely on self-
attention, whose computation is permutation-equivariant and therefore lacks an intrinsic mechanism for representing
token order. Existing architectures address this limitation by explicitly incorporating positional information through learned positional
embeddings or hand-crafted positional encodings, such as rotary positional encoding (RoPE), treating positional information as an architecturally acquired capability rather than an inherent property of the model. Motivated by the pursuit of positional-encoding-free architectures, this work explores a
language model architecture that integrates causal state-space equations to implicitly encode positional information before
attention computation. Specifically, each model block applies a causal state-space equation before self-
attention, allowing recurrent state dynamics to encode sequential information into
token representations. Consequently, subsequent
attention layers operate on position-aware representations without requiring explicit positional encodings while retaining the expressive modeling capacity of self-
attention. We present ZetaGPT, a compact hybrid
language model designed for research, rapid prototyping,
algorithm verification, and educational applications. In addition to the proposed architecture, ZetaGPT provides a fully open-source, end-to-end training pipeline encompassing
dataset construction, tokenizer training, pretraining, supervised fine-tuning, reinforcement learning from human feedback (RLHF), and chain-of-thought (CoT)
reasoning via pure reinforcement learning. To the best of our knowledge, ZetaGPT is the first open-source small
language model without explicit positional encoding and establishes a compact, reproducible reference implementation for the development and empirical study of positional-encoding-free
language models.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
LITEWAY: LIghtweight HAR via Temporal Efficient highWAY
Dominique Nshimyimana, Vitor Fortes Rey, Mengxi Liu et al. (+2 more)
Wearable human activity recognition (HAR) remains challenging due to the computational and energy constraints of deep learning models on resource-limited devices. Existing lightweight approaches often rely on recurrent architectures (e.g., GRU and LSTM), limiting parallelism and increasing inference latency. We propose LITEWAY, a modality-agnostic, fully convolutional framework for multichannel sensor time series that replaces recurrent temporal modeling with structured convolutional decomposition. LITEWAY combines lightweight convolutional blocks, strided temporal processing, and convolution-
attention pooling to efficiently capture temporal dependencies while reducing computational complexity. We evaluate LITEWAY on 16 HAR
datasets against TinyHAR, TinierHAR, and MLP-HAR. LITEWAY achieves competitive macro F1 while reducing model size by 4.06x-9.52x (Light) and 3.87x-9.07x (Full) compared with TinyHAR and TinierHAR. Deployment experiments further show energy reductions of 2.29x-3.14x (Light) and 1.46x-2.01x (Full) compared with TinierHAR and MLP-HAR, highlighting efficient fully convolutional temporal modeling for wearable HAR. The source code is publicly available at https://github.com/dominique-nshimyimana/liteway.
Read the full abstract ▾
All authors Dominique Nshimyimana, Vitor Fortes Rey, Mengxi Liu, Bo Zhou, Paul Lukowicz
Artificial Intelligence
KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models
Chen Qiu, Ziwu Liu, Chao Fei et al. (+2 more)
KV-cache compression reduces long-context
memory, but aggregate task scores reveal neither which correct executions fail nor why. We present KVDiagnosis, a diagnostic
dataset and
benchmark with three contributions. First, a 25-method taxonomy groups methods into five mechanism families and links them to eight verified implementations and their valid diagnostic measurements. Second, for every supported method setting, we evaluate all sources in each fixed split against a per-source FullCache control before selecting FullCache-correct/compressed-wrong (C-to-W) rows separately for each method-setting, so no compressor defines another's test set. Third, a common record format links paired outputs and run metadata to cache, likelihood,
attention, and decoding measurements with explicit applicability states. On Qwen3-8B, four evidence-aware workloads yield 59 800 supported compressed runs over 2600 sources and 12 520 C-to-W rows. Under fixed diagnostic rules, 63.2% have low or partial measured/projected coverage. Only 19 rows (0.2%) combine high measured/projected coverage with strong likelihood drift; another 2,126 (17.0%) preserve structural position addressability, for which representation fidelity remains unknown, while showing the same drift. Against C-to-C success controls, all ten diagnostics separate failed from successful compression (stratified AUROC 0.684-0.871). Among 96 reproducible low-EAR failures, a controlled 4x evidence-
attention boost repairs 29.2%, versus 6.3% under a count-matched sham intervention and 3.3% degradation on matched C-to-C controls. Code and data are available at https://github.com/ChosenQC/KVDiagnosis.
Read the full abstract ▾
All authors Chen Qiu, Ziwu Liu, Chao Fei, Guozhong Li, Panos Kalnis
Artificial Intelligence · Cross-listed from cs.CV
Sign Language Recognition Using Original and Synthetic Depth Image Based Point Cloud Data Models
Rustem Ozakar and Eyup Gedikli
Research regarding the sign
language recognition mostly relies on RGB images, whileas sign
language datasets that provide depth images are limited. Point clouds obtained from depth images can be used for sign
language recognition with neural networks like PointNet. In recent years, various neural networks are used for generating realistic depth images from
monocular RGB images. In this work, synthetic depth images were created from RGB images using Depth Anything V2 network. For this purpose, three sign
language datasets (Real-time ASL Fingerspelling, KArSL, AUTSL) which contain both RGB and depth images were used. Classification accuracies of the point cloud data created from both original and synthetic depth images using various PointNet architectures were measured for sign
language recognition. From the original and synthetic point clouds, frame based, Point Gesture Map and Long Short Term
Memory data models were used for classification and their performances were compared. In the results, both original and synthetic based data achieved acceptable performance in most models. In general, original depth based point cloud models performed better than synthetic ones, however in some models synthetic depth based models performed better than the originals.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.DB
Monotonicity-Guided Bottom-Up Petri Net Discovery: The SPECpp Framework
Leah Tacke genannt Unterberg, Lisa L. Mannel and Wil M. P. van der Aalst
Process discovery is one of the central challenges in process mining. Petri nets are particularly attractive because simple local constructs can express complex behavior, including concurrency. While their global behavior may be difficult to analyze, individual places can be efficiently characterized using monotonic properties, enabling bottom-up discovery. Unlike top-down approaches such as the Inductive Miner, which rely on predefined constructs for sequences, choices, loops, and concurrency, our approach allows such structures to emerge organically and can exploit the full expressive power of Petri nets, including free-choice constructs and long-term dependencies. The main challenge is the exponential number of candidate places and their combinations. We present the SPECpp framework which implements strategies to obtain high-quality models under time and resource constraints. SPECpp supports rapid experimentation and is used to evaluate these strategies using both synthetic and real-life event data.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law
Rose Cymbler, Daniel Guez and Laurent Fabre
We identify and quantify temporal misgrounding: the systematic
retrieval and citation of the currently in-force version of a legal article when the applicable version is an earlier or future one. Standard legal RAG treats the corpus as static; we argue legal question answering is a temporally-indexed
retrieval problem. We introduce FiscalQA Pro, pairing a versioned corpus of 32,436 article-versions of the French tax code (93 years, 1938-2031) with an all-model-hard temporal-
reasoning track: 209 scored, expert-reviewed questions across 33 CGI articles (221 released; twelve flagged out of the answerable scope). At selection time, no evaluated model recovered its date-applicable answer closed-book in any of four sampling draws, and the currently in-force text lacks the gold value for all but one of the scored questions. Answers are scored deterministically via atomic ground-truth "nuggets" (regex and numeric-with-tolerance), never LLM-as-judge: an LLM judge would inherit the temporal bias it is meant to score. Across eleven models (five frontier closed-API systems plus Gemini 2.5 Pro as a substitute entry, and five open-weight), parametric knowledge yields 3.0% mean strict accuracy and RAG over a static current-version corpus 2.7%. Static RAG retrieves the date-applicable version 0% of the time, confidently citing a real but inapplicable version. Our end-to-end retriever over a multi-version index, with no oracle, reaches 98.3% mean strict; an oracle-article ablation reaches 99.1%, locating the residual gap in first-stage recall, not version selection. We additionally release a version-aware jurisprudence
dataset of 69,208 citation links, together with the corpus,
benchmark, model responses, and pipeline code.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Imaginative Generative AI: Crossing the Entropy Wall into Worlds Beyond Imitation
Farzan Farnia, Hossein Goli and Amin Gohari
Generative AI models are primarily designed to imitate the data distribution, an objective that neither corrects diversity lost by a learned generator nor defines how generation should extend beyond the diversity of the data itself. We introduce Imaginative Generative AI (IGA), a framework that makes diversity part of the target-distribution design problem: among distributions close to a reference, IGA selects one whose spectral diversity reaches a prescribed level. Diversity is measured by the von Neumann
entropy of the generated distribution's kernel covariance operator in a fixed representation space, providing a reference-free representation-guided measure of how broadly probability mass occupies
embedding directions. The spectral
entropy of the population data distribution defines an
Entropy Wall. Below the wall, IGA performs diversity repair, recovering variation that a learned generator has lost while remaining within the diversity level of the data. Beyond the wall, the data distribution itself becomes infeasible, and IGA deliberately departs from it to produce distributions with greater representation-relative spectral diversity, an operational notion of imaginative generation. These regimes form a single regularization path from imitation to imagination and define an i.i.d. target distribution at each prescribed diversity level. We develop the theory of this
entropy-constrained projection and show that, under a KL anchor to a pretrained generator, the optimum satisfies a self-consistent exponential-tilt relation. This characterization leads to IGA Guidance, a retraining-free inference-time method for score-based and
diffusion models, including DDPM and DDIM samplers. Experiments on synthetic and
vision benchmarks demonstrate diversity repair below the
Entropy Wall and controlled spectral extrapolation beyond it.
Read the full abstract ▾
Artificial Intelligence
OpenLoopEvolve: A Verifiable Self-Evolution Framework for Loop Policies in Long-Horizon Complex Tasks
Siqi Wang, Xinlin Li, Zhenglin Li et al. (+1 more)
Long-horizon complex tasks require
agents to repeatedly observe states, formulate plans, invoke tools, verify results, and recover from failures in continuously changing environments. However, such control experience often remains confined to a single context or a fixed
prompt, and is difficult to accumulate and reuse across historical traces. This paper presents OpenLoopEvolve (OLE), a self-
evolution framework centered on the Loop Policy. OLE represents an
agent's observation, planning,
memory, action, verification, recovery, stopping, and budget control as portable policy assets with versions and lineages, and provides online and offline
evolution modes that can be selected according to practical needs: the online mode triggers candidate generation based on feedback from continuous operation, whereas the offline mode searches for candidate policies from archived traces and failure evidence. Both modes share an
evolution mechanism consisting of autonomous proposals by a large
language model, Champion–Challenger paired evaluation, and robust release. Policies released online are activated at a subsequent task boundary, monitored using subsequent feedback, and rolled back to their parent versions when degradation conditions are met. On the simulated business
benchmark YC-Bench, both modes improve aggregate task performance, task success rate, and risk metrics relative to a fixed initial Loop Policy. The results indicate that treating the Loop Policy as a governable asset can support the accumulation, comparison, release, and reuse of control experience and improve
agent performance on long-horizon complex tasks.
Read the full abstract ▾
All authors Siqi Wang, Xinlin Li, Zhenglin Li, Li Li
Artificial Intelligence
CircuitReason-1k: Benchmarking Long-Horizon Visual-to-Symbolic Reasoning inElectrical Circuits
Xinqi Yang, Kang An, Tengyue Wang et al. (+8 more)
Electrical
circuit analysis requires more than recognizing components in an image. A solver must ground symbols and labels, recover latent
topology, select a physical model, formulate coupled equations, propagate intermediate quantities, and preserve units, signs, directions, and phase conventions. We introduce \benchmark, a
benchmark of 1,000 authentic textbook problems for evaluating this complete long-horizon visual-to-symbolic
reasoning process. Each problem pairs one or more
circuit diagrams with a self-contained question, a typed or semantically specified answer, and a reference worked solution. An evidence-first construction pipeline aligns questions, figures, and solutions, while a
reasoning-oriented taxonomy organizes problems by
circuit type and dependency depth. Evaluation combines conservative typed scoring with identity-blinded multi-model semantic consensus, retaining every problem in the denominator. Across three commercial chatbot systems and six open-source
multimodal large
language models, the highest-scoring system reaches 84.8% accuracy. However, performance consistently deteriorates on long-horizon problems, and qualitative analysis exposes persistent failures in
topology-to-target binding, physical conventions, and late-stage output propagation. \benchmark{} provides a focused testbed for measuring whether
multimodal models can transform technical visual evidence into sustained, physically valid symbolic
reasoning. Code are available at GitHub - CircuitReason/CircuitReason1K.
Read the full abstract ▾
All authors Xinqi Yang, Kang An, Tengyue Wang, Zhongyu Yang, Chenxu Du, Yuanchi Zhu, Hebao Zhu, Ziliang Wang, Faqiang Qian, Yunli Yang, Qibing Ren
Artificial Intelligence · Cross-listed from cs.CV
FeedbackTrack: Visual-Cortex-Inspired Cross-Frame Feedback for Transformer Tracking
Yueyang Cang, Xiaoteng Zhang, Zhiyuan Ning et al. (+2 more)
Visual object tracking requires effective temporal integration, yet most
Transformer trackers still rely on predominantly feed-forward feature extraction. Existing temporal mechanisms typically update templates,
prompts, queries, or prediction states, while intermediate representations are rarely reused to modulate corresponding processing stages. We propose FeedbackTrack, a visual-cortex-inspired framework that introduces sparse, group-level layer-aligned cross-frame feedback into pretrained
Transformer trackers. Previous-frame intermediate states are detached, cached, and returned to corresponding
Transformer groups in the current frame through two lightweight pathways: Query Feedback for
token-level query modulation and Gate Feedback for context-dependent feature modulation. FeedbackTrack preserves the original tracking pipeline with only a fixed-size one-frame cache. Across SPMTrack and ARTrackV2, FeedbackTrack consistently improves five backbone configurations on LaSOT and GOT-10k, achieving 83.4 AO and 79.1 AUC with SPMTrack-G while adding less than 1% parameters. Controlled comparisons show that cross-frame feedback outperforms same-frame modulation by 1.8–3.2 AO points, demonstrating that the gains mainly come from recurrent historical information. Further analysis reveals a non-uniform depth-dependent organization of learned feedback strengths, highlighting the effectiveness of recurrent feedback for
Transformer tracking.
Read the full abstract ▾
All authors Yueyang Cang, Xiaoteng Zhang, Zhiyuan Ning, Yuchen He, Li Shi