Artificial Intelligence
Reputation-driven Cooperation in Lattice-based Decentralized Federated Learning through Evolutionary Game Theory
Phuc Hoang Truong Huynh, Dung Tran Vinh, Khoa Duc Anh Lam et al. (+9 more)
Decentralized
Federated Learning (DFL) has emerged as an optimal
privacy-preserving solution; however, it remains vulnerable to opportunistic behaviors due to the absence of a central coordinator. While Evolutionary Game Theory (EGT) serves as a powerful framework for analyzing such behaviors, existing studies often assume that
agents possess perfect rationality and maintain static strategies. To address these limitations, this paper proposes a novel EGT framework designed to analyze strategic
evolution and enhance overall system performance. The primary contributions of this work are threefold: First, we model peer-to-peer (P2P) interactions on a
lattice network structure under the assumption of bounded rationality. Second, we formulate a comprehensive payoff
matrix incorporating training costs, communication overhead, and cooperative rewards, while tailoring a strategy update rule that captures spatial propagation dynamics. Third, we integrate a reputation-based reward-and-punishment mechanism to effectively deter free-riding behaviors. Simulation results demonstrate that the framework significantly outperforms the baseline. Specifically, it increases average accuracy from approximately 70% to 82%, elevates cooperation frequency to approach 100% (compared to below 5% in the baseline), and drops accuracy variance from around 0.40 to 0.002, thereby accelerating uniform convergence and ensuring system stability.
Read the full abstract ▾
All authors Phuc Hoang Truong Huynh, Dung Tran Vinh, Khoa Duc Anh Lam, An Nghiem Nguyen Truong, Uyen Nha Tran Bui, Khang Nguyen Dinh, Bao Nguyen Le Gia, Minh Le Nguyen Nhat, Manh Hong Duong, The Anh Han, Thi Ai Thao Nguyen, and Le Hong Trang
Artificial Intelligence
Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races
Phu Hoa Pham, Duy Minh Dao Sy, Trung Kiet Huynh et al. (+9 more)
An AI development race creates a multi-
agent safety dilemma. Each company can develop slowly and safely, or move faster while taking a risk that may remove its final reward. We use this repeated game to study strategic safety behaviour among large
language model (LLM)
agents in races with two to five players. However, a valid action does not show that an
agent understands the game. We therefore place an audit gate before behavioural interpretation. We first verify the game engine, then test rule recall, state tracking, payoff calculation, and stability under different but equivalent task descriptions. We then compare LLM action sequences with an evolutionary game-theory
benchmark and published human data, and explore differences across models, risk conditions, personas, and two- to five-player races. The audit shows that strong rule recall can coexist with weak state tracking and expected-payoff calculation. Providing verified arithmetic and changing the response representation can also change later actions, even when the game rules stay fixed. Across seven tested model endpoints, aggregate rates hide large differences in action sequences, responses to opponents, and responses to race position. Patterns across the tested three- to five-player races are also model-specific rather than a single effect of adding competitors. These results show why multi-
agent AI-race simulations need validity checks and trajectory-level analysis before their outputs are described as strategic, human-like, or safety-aware. Our findings are exploratory and apply only to the tested models,
prompts, and decoding settings.
Read the full abstract ▾
All authors Phu Hoa Pham, Duy Minh Dao Sy, Trung Kiet Huynh, Phu Quy Nguyen Lam, Chi Nguyen Tran, Minh Trung Le, Phong Hao Le, Dinh Nam Nguyen, Thien Ky Nguyen Dong, Elias Fernandez Domingos, Le Hong Trang, The Anh Han
Artificial Intelligence
Co-evolution of social reward and punishment under institutional interventions
Van An Nguyen, Vuong Khang Huynh, Hoai Thuong Nguyen et al. (+14 more)
We investigate how peer and institutional incentives jointly shape the
evolution of cooperation, social welfare, and enforcement efficiency in social dilemmas. In a Prisoners Dilemma with four strategies, unconditional cooperators (C), defectors (D), social punishers (SP), and social rewarders (SR), we allow decentralised peer incentives and centralised institutional incentives to act simultaneously, with the institution able to reward or punish any subset of strategies. In infinite well-mixed populations, we analyse the resulting four-strategy replicator dynamics, and in structured populations we use
agent-based simulations on square
lattices to study spatial effects and network reciprocity. Intervention schemes are evaluated by
equilibrium states and evolutionary flow for infinite well-mixed populations, by cooperation levels and social welfare for structured populations, defined as aggregate population payoff net of institutional cost. We find that peer punishment most strongly promotes cooperation, whereas peer reward is more beneficial for social welfare. Institutionally rewarding peer incentive strategies substantially improves both cooperation and welfare, while subsidising unconditional cooperators has little impact. Under institutional punishment, directly penalising defectors is the only consistently effective policy; punishing peer incentive strategies dismantles decentralised incentives, reduces cooperation, and harms social welfare, showing that maximising cooperation does not necessarily optimise overall societal benefit. Our findings provide design principles for institutions seeking to balance cooperation promotion with welfare maximisation.
Read the full abstract ▾
All authors Van An Nguyen, Vuong Khang Huynh, Hoai Thuong Nguyen, Duc Tin Duong, An Nguyen Gia, Tat Kien Nguyen, Huu Loi Bui, My Nguyen Tra, Ho Nam Duong, Ba Thanh Phan, Thanh Vo, Dinh Anh Trung Hoang, Adeela Bashir, Zhao Song, Manh Hong Duong, Le Hong Trang, The Anh Han
Artificial Intelligence · Cross-listed from econ.GN
Talking to Digital Twins: Selective Disclosure and Belief Measurement in Financial Social Media
Boone Bowles, Raymond Duch and Sorin Sorescu
Social media affect financial
markets, but public posts by financial media personas are voluntary disclosures. What is not disclosed is therefore usually unobserved. We address this measurement problem by conducting repeated, real-time interviews of "digital twins" built from monitored finfluencers' X accounts under a fixed protocol. The interviews recover stock-level public-persona belief proxies even when no public recommendation is made. Because the interviews are generated and archived before the relevant return windows, the design avoids the look-ahead bias that arises when LLMs are queried ex post. The evidence shows that information obtained from these digital-twin interviews predicts the cross section of large-cap stock returns in the expected direction. Repeated real-time interviews therefore show how selective disclosure can be turned into measurable panels of
market views.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
DynActiveGS: Active Gaussian Splatting for Dynamic Scene Reconstruction
Hongbo Duan, Pengting Luo, Chengzhi Zhao et al. (+3 more)
We present DynActiveGS, a dynamic-aware active reconstruction framework based on 3D Gaussian Splatting (3DGS) for autonomous exploration in dynamic environments. The framework incrementally reconstructs a 3D Gaussian scene representation while suppressing motion-corrupted observations through online uncertainty prediction and uncertainty-weighted Gaussian optimization. A key component of DynActiveGS is the explicit decomposition of uncertainty into structural uncertainty and motion-induced uncertainty, which enables the system to distinguish under-reconstructed static regions from dynamically unreliable areas. Based on these uncertainty fields, DynActiveGS performs dynamic-aware viewpoint selection and dynamic-constrained path planning to favor informative yet stable observations during exploration. The resulting system forms a unified closed-loop pipeline for robust active reconstruction in dynamic scenes. Extensive experiments on challenging dynamic
benchmarks demonstrate consistent improvements over existing active reconstruction baselines in reconstruction accuracy, completeness, rendering quality, and exploration efficiency.
Read the full abstract ▾
All authors Hongbo Duan, Pengting Luo, Chengzhi Zhao, Yuanhao Chiang, Fangming Liu, Xueqian Wang
Artificial Intelligence
The Graph Language: How Knowledge Graphs Speak to Large Language Models
Giuseppe Pirrò
Large
Language Models (LLMs) excel at
reasoning but benefit from grounding provided by Knowledge Graphs (KGs). However, integrating these paradigms is challenging. We introduce GRALAN, which enables KGs to speak directly in the LLM's semantic space through relational
tokens that preserve graph structure. GRALAN-s trainable
language mediator generates structured
tokens for any frozen LLM, creating a foundation for knowledge-intensive applications. We demonstrate its effectiveness in question-answering by re-framing the task as entity classification over question-focused subgraphs. Experiments show that GRALAN significantly outperforms existing methods, particularly on complex multi-hop
reasoning tasks, establishing a new paradigm for KG-LLM integration that maintains structural fidelity while leveraging LLMs'
reasoning capabilities.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CE
Hybrid Lagrangian-Eulerian Model for Lagrangian Fluid Simulation
Ruoyan Li, Wei Wang and Yizhou Sun
Pure Lagrangian neural simulators offer
geometric flexibility and exact advection, making them well-suited for modeling moving domains and free surfaces. However, the absence of a fixed global reference frame introduces two severe limitations: a spatial bottleneck, in which model capacity is wasted on uniform regions because the dense particle neighborhoods required for stable gradients are applied indiscriminately, and rapid temporal drift, caused by purely local message passing that lacks a global anchor. Inspired by classical hybrid numerical solvers, we propose a Hybrid Lagrangian-Eulerian neural simulator that augments Lagrangian dynamics with an Eulerian representation. To address the spatial bottleneck, we introduce adaptive downsampling that eliminates kinematic redundancy, preserving micro-scale details on particles while aggregating compressed features onto Eulerian nodes to resolve large-scale dynamics. To counter temporal drift, we employ a cross-
attention mechanism that queries these Eulerian features, using the fixed grid as a stable spatial anchor to correct trajectory deviations at every timestep. Comprehensive experiments show that this hierarchical, cross-attended design substantially suppresses error accumulation, establishing a new state-of-the-art for accuracy and rollout stability in Lagrangian fluid simulation.
Read the full abstract ▾
Artificial Intelligence
PATH-Bench: Path-Dependent Evaluation of Lifelong Agents
Xidong Yang, Xingyi Zhang, Wenhao Li et al. (+7 more)
Lifelong LLM
agents increasingly adapt through external learning states that store past interactions as retrievable
memories or reusable skills, yet existing
benchmarks rarely account for how the path of accumulated experience shapes what
agents transfer and retain. In this work, we establish PATH-Bench, a
benchmark for path-dependent evaluation of lifelong
agents. PATH-Bench estimates directed task relationships via multi-model in-context learning, constructs probe-centered sequences with controlled helpful and interfering histories, and repeatedly evaluates probe tasks to measure average performance, forward transfer, backward transfer, and forgetting. We evaluate eight representative
agents on single-turn code generation and multi-turn tool-use tasks under positive- and negative-dominant histories.
Benchmark results show that experience utility depends jointly on how experience is represented and on the task's interaction structure, that strong transfer does not ensure retention, and that later experience can reshape gains acquired earlier in the learning path. Based on these findings, we propose Selective Experience Use (SEU), an
agent harness that regulates how path-accumulated experience influences each new task, admitting helpful items while filtering out potential interference. SEU consistently reduces forgetting while improving forward transfer in the majority of settings. The PATH-Bench provides both a controlled evaluation framework and actionable guidance for designing more selective and robust lifelong
agents.
Read the full abstract ▾
All authors Xidong Yang, Xingyi Zhang, Wenhao Li, Wenyan Liu, Junjie Sheng, Yun Hua, Wei Yin, Tao Fang, Chuyun Shen, Xiangfeng Wang
Artificial Intelligence · Cross-listed from cs.LG
Policy Optimality Measurement for Multi-Vehicle Decision-Making: From Extrinsic Indicators to Intrinsic Quality
Ye Han, Lijun Zhang and Dejian Meng
Evaluating Multi-
Agent Reinforcement Learning (MARL) policies in autonomous driving fundamentally relies on extrinsic statistical indicators (e.g., reward curves and success rates), which often mask intrinsic policy degradation and algorithmic blind spots. To break this black-box evaluation, this letter proposes a novel information-theoretic diagnostic framework. By leveraging a fully converged Monte Carlo Tree Search (MCTS) as an asymptotic oracle, we establish a theoretical ground-truth baseline distribution. We formulate a bounded policy optimality score ($\mathcal{M}_{opt}$) using the forward KL divergence to rigorously penalize fatal collaborative omissions. Crucially, we semantically decouple this metric into lateral and longitudinal dimensions, creating a granular "semantic microscope". Extensive spatial and temporal diagnostics on state-of-the-art MARL architectures and exploration mechanisms demonstrate that our framework conclusively exposes hidden directional biases, identifies temporal average-policy traps, and transforms heuristic hyperparameter tuning into a visually trackable trajectory optimization. This framework establishes a rigorous, model-agnostic standard for benchmarking intrinsic multi-
agent policy quality.
Read the full abstract ▾
Artificial Intelligence
MA-HEAD-Net: Adaptive Rule-Guided Multi-Agent DRL for AoI Minimization in UAV-Assisted Emergency Networks
Yixin Zhang, Zhuohui Yao, Wenchi Cheng et al. (+1 more)
In post-disaster scenarios, unmanned aerial vehicles (
UAVs) are critical for establishing emergency communication networks. For time-critical rescue missions, information freshness is crucial because decisions based on outdated data may lead to ineffective control actions. This paper investigates age of information (AoI) minimization for
UAV-assisted emergency communications with heterogeneous emergency services. We model bursty packet arrivals using a Markov-modulated Poisson process and adopt finite blocklength theory to capture the coupling among transmission duration, packet completion, and AoI
evolution. To balance delay-tolerant long-packet transmission and urgent short-packet response, we propose a mini-slot-embedded scheduling mechanism with adaptive checkpoint-interval selection. We formulate the joint optimization of
UAV trajectory control, user scheduling, and checkpoint-interval selection as a multi-
agent decision problem, and develop MA-HEAD-Net, an adaptive rule-guided multi-
agent deep reinforcement learning framework. MA-HEAD-Net incorporates communication-domain rule priors into a gated multi-head policy, where adaptive gates regulate the contributions of rule-prior and learned-policy logits for different subtasks. The policy and gating components are jointly optimized under multi-
agent proximal policy optimization. Simulation results show that MA-HEAD-Net improves policy-formation efficiency compared with representative multi-
agent deep reinforcement learning baselines and achieves lower AoI than both learning-based and heuristic methods in dynamic
UAV-assisted emergency communication scenarios.
Read the full abstract ▾
All authors Yixin Zhang, Zhuohui Yao, Wenchi Cheng, Walid Saad
Artificial Intelligence
Fighting Fire with Fire: On the Feasibility of Protecting Exercises Against AI Cheating
Tobias Braun, Jonas Grebe, Louis Rethfeld et al. (+1 more)
The widespread adoption of generative AI enables students to outsource cognitive effort to increasingly capable assistants, creating an illusion of competence while undermining the independent
reasoning that education aims to cultivate. We investigate whether
adversarial machine learning can be repurposed to protect educational exercises against such corrosive reliance. Our approach uses
multimodal multiple-choice questions whose visual components can be protected with subtle visual perturbations that steer AI solvers toward designated incorrect answers. These responses form a statistical fingerprint: students who blindly copy a solver reproduce the induced answer pattern more frequently than genuine students. We study the feasibility of this paradigm under realistic black-box assistant assumptions using three of the most common state-of-the-art
multimodal language models: Anthropic's Claude, Google's Gemini, and OpenAI's ChatGPT. By using accessible surrogate models, we optimize
adversarial perturbations that induce consistent response patterns. Those patterns enable principled detection through statistical hypothesis testing. These findings establish both the promise and the limitations of fighting machine-assisted
reasoning with the vulnerabilities of the machines themselves.
Read the full abstract ▾
All authors Tobias Braun, Jonas Grebe, Louis Rethfeld, Marcus Rohrbach
Artificial Intelligence · Cross-listed from cs.CV
SG-Layout: Structured Scene Graph-Guided Layout Generation with LLMs
Junsheng Wang, Chao Chen, Mengying Xie et al. (+2 more)
Understanding and generating spatially coherent layouts from natural
language remains a fundamental yet challenging task for large
language models (LLMs). Existing LLMs often struggle to capture explicit
geometric relationships and structural dependencies between objects. To address this issue, we propose SG-Layout, a graph-guided layout generation framework that explicitly incorporates structured spatial knowledge into LLMs. SG-Layout follows a two-stage training paradigm: (1) a graph-
language feature
alignment stage, where a relational graph encoder and a projector are trained to map scene-graph
embeddings into the LLM's linguistic space; and (2) an instruction tuning stage, where LoRA-based adapters enable efficient fine-tuning for instruction-driven layout generation while keeping the backbone frozen. We evaluate SG-Layout on image layout generation, indoor scene synthesis and robotic object rearrangement tasks. Experimental results show that SG-Layout improves spatial
reasoning accuracy and
geometric consistency over the compact open-source backbone, with particularly clear advantages in relation-dense and compositionally complex scenes. These results highlight the effectiveness of graph-structured feature
alignment for enhancing controllable layout generation.
Read the full abstract ▾
All authors Junsheng Wang, Chao Chen, Mengying Xie, Mingyan Li, Fuqiang Gu
Artificial Intelligence · Cross-listed from cs.LG
FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intelligent Devices
Hongliang Zhang, Zhongyuan Yu, Fenghua Xu et al. (+3 more)
Federated learning (FL) enables multiple intelligent devices to collaboratively train a high-accuracy model without sharing raw data. However, due to its distributed nature, FL is vulnerable to Byzantine attacks. Existing defense methods rely on strong assumptions, such as the proportion of malicious devices not exceeding 50%, or the server having an additional root
dataset that matches the training task. Moreover, they show limited efficacy as they overlook $(i)$ the divergence among benign updates and $(ii)$ the curse of dimensionality involved in comparing two high-dimensional updates. To solve these concerns, we propose FL-OA, a Byzantine-robust
federated learning framework utilizing outsourced
auditing. In FL-OA, the server collaborates with third-party organization that holds an additional root
dataset to perform outsourced
auditing, thereby enabling the server to achieve robust aggregation without strong assumptions. Additionally, FL-OA introduces a gradient ascent step and a correction term during local training to mitigate the divergence among benign updates, and designs a parameter importance indicator to extract critical parameters for
auditing, alleviating the curse of dimensionality. We further provide a detailed theoretical analysis of FL-OA. Extensive experiments demonstrate that FL-OA outperforms existing defense methods against Byzantine attacks.
Read the full abstract ▾
All authors Hongliang Zhang, Zhongyuan Yu, Fenghua Xu, Teng Hu, Jian Meng, Jiguo Yu
Artificial Intelligence
Inter-Residue Geometry Attention for Antibody-Specific Epitope Prediction
Chuanliu Fan, Nan Yu, Junjie Wu et al. (+1 more)
Antibody-specific epitope prediction aims to identify which antigen residues are recognized by a given antibody, a task that depends on the three-dimensional complementarity between antibody CDRs and the antigen surface. Existing methods usually leverage PLM
embeddings and inject structure through additional graph, surface, or point-cloud encoders, where the positional mechanism inside
attention remains largely tied to one-dimensional sequence order. For
proteins, the analogue of a
token offset is not only sequence separation, but also the three-dimensional displacement between residues after folding. This raises a question, can folded residue geometry serve as the positional mechanism of
attention itself? We propose Local-Frame 3D Rotary Position Encoding (LF3DRoPE), which expresses inter-residue displacements in backbone-defined local frames and injects them directly into rotary
attention. This design preserves continuous directional geometry while ensuring invariance to global $\mathrm{SE}(3)$ transformations. On the AsEP
benchmark, LF3DRoPE achieves state-of-the-art $\mathrm{MCC}$ on both ratio and epitope-group splits. Ablations and rigid transformation tests show that local three-dimensional geometry provides information beyond sequence-order
attention while preserving invariance to arbitrary global coordinate systems. Mutation ranking results further indicate that LF3DRoPE captures antigen-specific structural compatibility.
Read the full abstract ▾
All authors Chuanliu Fan, Nan Yu, Junjie Wu, Guohong Fu
Artificial Intelligence · Cross-listed from cs.CL
Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization
Shigeng Wang, Chao Li, Yangyuxuan Kang et al. (+2 more)
We propose ScaleQ-1.58, a scalable ternary post-training quantization (PTQ) framework for
reasoning LLMs. Its core insight stems from an empirical finding: although modern LLMs are typically trained to exhibit chain-of-thought
reasoning capabilities, in the PTQ regime, even the latest CAT-Q method based on learning-based differentiable ternarization still leads to performance collapse on challenging mathematics and coding tasks when using conventional calibration schemes that ignore the model's
reasoning process. Driven by this finding, we introduce a simple calibration approach, Attend to Your Own Thoughts (AYOT), where
reasoning traces and final answers generated by the pre-trained high-precision target LLM on a proper set of calibration samples are used as the context input during the ternarization process, along with the corresponding questions. ScaleQ-1.58 is formed by simply integrating AYOT with CAT-Q, which demonstrates several scaling properties: (1) with only 4M calibration
tokens, Qwen3-1.7B ternarized by ScaleQ-1.58 reaches over 90.52% of the performance of the prior best BitNet b1.58 2B4T averaged over 4 mathematics and coding tasks, and our ternary Qwen3-4B shows an absolute gain of 8.97%, while requiring 1,000,000x fewer calibration
tokens for quantization; (2) ScaleQ-1.58 generalizes well to both dense and MoE architectures, with performance improving as model scale increases (up to 235B parameters); (3) ScaleQ-1.58 demonstrates strong generalization across tasks of varying difficulty levels, including mathematics, coding and scientific logic
reasoning, as well as commonsense
reasoning and basic
language generation; (4) its performance continues to improve as the number of calibration
tokens increases. Notably, AYOT also exhibits strong generalization ability across other quantization bit-widths. Code will be available at https://github.com/IntelChina-AI/BitTern.
Read the full abstract ▾
All authors Shigeng Wang, Chao Li, Yangyuxuan Kang, Jiawei Fan, Anbang Yao
Artificial Intelligence
Role-Decoupled Attention Residuals: Separating Matching and Content Retrieval Across Depth
Kehan Wang
Depth-routing residual architectures allow
Transformer layers to retrieve earlier representations instead of inheriting only the immediately preceding state. Existing Block
Attention Residuals, however, use a single content-dependent depth mixture to construct the inputs to queries, keys, and values. This design couples two functionally different decisions: queries and keys determine where
attention matches, whereas values determine what content is retrieved. We therefore ask whether matching and content
retrieval should be forced to read from the same depth. We introduce Role-Decoupled
Attention Residuals (RD-AttnRes), a minimal extension that shares one depth route between queries and keys while learning an independent value route over the same residual sources. Tying the two routing queries exactly recovers the parent architecture, while decoupling them adds only one model-width vector per layer and introduces no additional
token-to-
token attention operation. We evaluate RD-AttnRes using a frozen, paired pretraining protocol on FineWeb-Edu with five matched seeds for both 120M- and 343M-parameter models and a 2.0B-
token training budget. RD-AttnRes improves validation negative log-likelihood in all 10 matched comparisons. The mean reductions are 0.0301 and 0.0247, corresponding to perplexity reductions of 2.97 percent and 2.43 percent at 120M and 343M parameters, respectively. Early-budget controls indicate that neither the additional parameter count, duplicated routing execution, nor a fixed value route reproduces the improvement. Routing diagnostics further reveal persistent divergence between the query-key and value depth distributions. These results suggest that, within the evaluated training regime,
attention matching and content
retrieval benefit from distinct reads over the residual hierarchy.
Read the full abstract ▾
Artificial Intelligence
Control Under Compression: Reliability Frontiers for Tool-Using Agents
Yinghan Hou and Zongyou Yang
Tool-using
language-model
agents are governed not only by task
prompts but also by persistent system-side instructions that specify tools, arguments, policies, execution protocols, and recovery. Compressing these
agent control contexts (ACCs) can reduce input cost and context use, yet existing
prompt-compression evaluations do not reveal whether the resulting control remains operationally reliable. We introduce CompressAgent, an environment-verified
benchmark for ACC compression across nine independently constructed ACCs, three task families, three fixed Qwen API model identifiers, six retained-context budgets, and 15,525 runs. We uncover a nonlinear, method-dependent reliability frontier. At 75% retained context, generic rewriting and section-based compression achieve 92.7% and 92.4% success, close to the 93.8% full-context baseline. Between 50% and 35%, methods diverge sharply; at 35%, section-based, obligation-aware, and generic rewriting achieve 47.0%, 39.0%, and 19.9%. At retained-context budgets from 25% to 10%, executable protocols become fragile. Reliability also varies substantially across ACCs, making universal compressor rankings inappropriate and motivating per-context qualification. Failure analysis shows that compression primarily surfaces as tool-execution and action-parsing errors. These findings recast ACC compression from
token reduction into a runtime-reliability problem that must be evaluated through executable outcomes.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Credit the Right Box: Marginal Contribution Assignment for Structured Visual Perception
Xinheng Han, Jianfei Wang, Yu Chen et al. (+4 more)
Multimodal Large
Language Models (MLLMs) are increasingly expected to solve structured perception tasks that require visual recognition,
language-to-object binding, object cardinality preservation, and precisely localized grounding and
segmentation outputs. However, existing group-relative reinforcement learning methods provide only response-level supervision, creating a granularity mismatch for structured multi-object prediction: a single advantage is broadcast to all
tokens in a response, without distinguishing individual box contributions. To address this mismatch, we propose MCR-GRPO, a marginal contribution assignment framework that derives box-level credit directly from each sampled response. Specifically, Marginal Contribution Reward (MCR) estimates each predicted box's contribution through a leave-one-out comparison, measuring how the matched set value changes when the box is removed from the response. After within-response normalization, records that improve the set value receive positive credit, while redundant or harmful ones are suppressed. To make marginal attribution stable and informative, we further introduce a Continuous Matched Set Value Evaluator that integrates permutation-invariant matching, count-aware normalization, and graded localization. MCR-GRPO maps normalized box-level marginal advantages to the
token spans that generated each box, preserving GRPO's response-level comparison while enabling box-aware optimization of structured multi-object grounding. Experiments across REC, DOD,
segmentation, and counting
benchmarks show state-of-the-art performance over prior GRPO-based baselines.
Read the full abstract ▾
All authors Xinheng Han, Jianfei Wang, Yu Chen, Xiang Wang, Shuai Li, Weixing Li, Feng Pan
Artificial Intelligence
Don't Offer What Can't Be Done: Deterministic Executability Gating for LLM Skill Selection at Scale
Ortal Ashkenazi, Vitalii Kloz and Mykhailo Ulianchenko
Production LLM
agents that select from large skill libraries face a limitation that semantic relevance alone cannot resolve: a skill may match a user's topic yet be impossible to execute in the current account state. We present a deployed three-stage selection pipeline for Helpmate, Wix's customer-care assistant. First, a recall-oriented semantic matcher identifies messages related to a ten-skill domain family without consulting account state. Second, a deterministic executability gate removes candidates whose internal hard-stop conditions hold. Because the gate and the skill evaluate the same exit predicates, every blocked candidate would be unable to complete under the same account state, provided predicate parity is preserved and both checks observe fresh authoritative state. Finally, the LLM decides whether to invoke one of the remaining candidates. In a post-launch production analysis of 756.6K user messages across 267.6K conversations, semantic matching retained 174,927 messages (23.1%). Within this matched stream, the gate removed 1,039,462 of 1,749,270 skill-message pairs (59.4%), saving 228.8 million skill-description
tokens – 59.1% of the post-semantic skill-description footprint. Together, semantic matching and executability gating reduced skill-description context by 90.5% relative to exposing all ten skills to every message. To test whether this
pruning affects model behavior rather than context size alone, we replayed a risk-enriched cohort of 1,000 conversations with all ten skills exposed. The model selected a production-blocked skill in 78 conversations (7.8%). This counterfactual result shows that deterministic gating prevents non-executable candidates from influencing model selection, while not claiming downstream tool execution or customer-outcome effects.
Read the full abstract ▾
Artificial Intelligence
FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds
Kapil Wanaskar, Gaytri Jena, Aman Chadha et al. (+3 more)
World models have attracted significant
attention for their ability to capture and predict the structure and dynamics of the physical world. In this emerging landscape, Joint
Embedding Predictive Architectures (JEPA) offer a particularly compelling direction. We study a largely unexplored regime: populous, crowded, and chaotic Global South urban environments, which we call DENSEWORLD. Unlike the lower-density, lane-structured settings that dominate existing evaluations, these scenes exhibit soft spatial boundaries, extreme
agent heterogeneity, persistent occlusion, and rapid social negotiation under mixed traffic. We introduce the first large-scale
dataset for this regime: 1,000 hours of drive-through, walk-through, and aerial
video across 22 cities. Existing JEPA formulations struggle to preserve dense interaction dynamics under heterogeneity and partial observability. We introduce FactorJEPA, which makes world structure a first-class predictive primitive. Rather than encoding the future in a monolithic latent, it composes layout, entities, and interactions, using a visibility gate and separated subspaces to preserve partially observed
agents and discourage cross-factor shortcuts. FactorJEPA improves (i) future-latent accuracy (Future-frame L1), (ii) intervention-sensitive prediction (Causal L1), and (iii) robustness to reduced visual evidence (Mask-ratio slope), while exposing (iv) a reproducible motion-information trade-off (Motion cosine). Method rankings replicate across 2B and 1B V-JEPA 2.1 backbones, with rho = 0.895 to 0.978. We publicly release the DENSEWORLD-115k
dataset (https://huggingface.co/
datasets/anonymousML123/denseworld-115k) and the surgery-trained FactorJEPA checkpoints (https://huggingface.co/
datasets/anonymousML123/factorjepa-outputs/tree/main/outputs/full/vjepa_2_1_vitg_1B/train/m09c_surgery_3stage_DI_diheavy_encoder).
Read the full abstract ▾
All authors Kapil Wanaskar, Gaytri Jena, Aman Chadha, Vinija Jain, Vasu Sharma, Amitava Das
Artificial Intelligence · Cross-listed from cs.CL
DeBERTa-Sentinel: Toward Transparent and Trustworthy Detection of AI-Generated Text
Muhammad Yousaf Rehman and Muhammad Islam
The rapid spread of large
language models (LLMs) across the web raises concerns about misinformation, academic integrity, automated content manipulation, and risks to vulnerable online communities. Existing
transformer-based detectors, such as GPT-Sentinel, show promise but struggle to generalize to diverse model outputs and paraphrasing attacks, limiting their role in building trustworthy web ecosystems. This work introduces DeBERTa-Sentinel, a responsible AI-generated text detection framework leveraging DeBERTa-v3's disentangled
attention to capture subtle structural irregularities in synthetic content. A central design principle is transparency: unlike black-box commercial detectors, DeBERTa-Sentinel exposes
token-level explanations of its decisions, enabling affected stakeholders journalists, educators, and platform trust and safety teams to audit, challenge, and contextualize detection outcomes. Using the GLC-AIText
dataset of 28,057 human and LLM-generated samples (GPT, LLaMA, and Claude) with a 60-20-20 split, DeBERTa-Sentinel achieves 98.21% validation accuracy and surpasses the RoBERTa-Sentinel baseline from NeurIPS 2025, achieving 97.53% test accuracy, 95.89% precision, 99.33% recall, and 99.53% ROC-AUC, and maintaining a 0.665% false negative rate. The model's interpretability reveals linguistic markers such as academic phrasing and formal transitions associated with synthetic text, directly supporting stakeholder needs for verifiable, auditable content-authenticity decisions. By advancing responsible detection methods that reduce bias and enhance explainability, DeBERTa-Sentinel promotes trustworthy, ethical, and human-centric AI systems. Code and data are available at https://github.com/Galileo-Galili/HUMAN-VS-AI-TEXT-DETECTION.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks
Haoyu Zhang, Xiangchen Guan, Shibo Zheng et al. (+2 more)
We report a counter-intuitive interaction between image inputs and existing black-box defenses on
Vision–
Language Models (VLMs): pairing an encoded jailbreak
prompt with an unrelated decoy image can sharply lower attack success rate (ASR). The operative change is in the defense pipeline, not in the image. Across five frontier VLMs, two encoded-attack families, and three black-box defenses, a caption-mediated defense (ECSO) that leaves ASR essentially unchanged on text-only encoded input drops it by up to $73$pp once a content-free decoy is attached; every non-saturated contrast is significant under exact McNemar tests. We advance two hypotheses for this pattern, supported by indirect evidence rather than pipeline introspection, since a black-box threat model precludes inspecting vendor internals: caption-mediated defenses branch on image presence, and intrinsic image-side safety engages on image-resident content. Three controls constrain the explanation. Blank-canvas and natural-photograph decoys reproduce the effect on every model, implicating image presence rather than content; the effect replicates on three open-weight VLMs served with no moderation layer, so it is not a vendor-filtering artifact; and a non-symbolic, meaning-based encoder reproduces it, so it is not specific to symbolic obfuscation. Attaching a decoy unconditionally is not deployable — it raises benign refusal to $20$–$79\%$, an inflation of $+10$ to $+67$pp — but gating attachment on a lightweight encoded-input detector returns benign refusal to the text baseline while preserving the safety gain wherever the detector fires, making detector recall the binding constraint. Under adaptive attacks that target the caption-mediated re-check, the effect degrades but holds. We frame this as an observation about pipeline interaction, not as a robust defense.
Read the full abstract ▾
All authors Haoyu Zhang, Xiangchen Guan, Shibo Zheng, Mohammad Zandsalimy, Shanu Sushmita
Artificial Intelligence · Cross-listed from cs.SE
What Could the Agent See at 19:05? Generating Temporal Enterprise Scenarios from Real Research and Replaying Them to Evaluate Agents
Tezan Sahu and Himani Arora
Enterprise AI
agents act across many apps whose data changes continuously, so an answer is correct only relative to what data existed and who could see it at the moment it was asked. Offline evaluation today grades against a single static snapshot, effectively the end of the episode. So, it can only evaluate one situation, the final one, even though every earlier moment of the episode is a different situation that invites its own realistic questions with its own correct answers. Recreating each of those moments as a separate snapshot would mean re-provisioning a whole tenant per instant, which is prohibitively costly; and even a single snapshot leaks future state hidden inside records and cannot represent the multi-app, time-ordered way real work happens. Our system closes two gaps at once: it generates a realistic, persona-driven, temporally-evolving enterprise world from real research, and replays that world at any chosen moment to evaluate any pluggable
agent. A schema-inferred temporal description drives a deterministic-plus-LLM rebuild of each record's past state; because the queryable moments are finite, all rebuilds are precomputed into a compact difference cache, making evaluation a fast, reproducible lookup with no model in the path. We describe the design, an architecture spanning both flows, and early experience evaluating enterprise
agents.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA
Zhihao Zhu, Hanlin Shang, Mingwang Xu et al. (+6 more)
Vision-
Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential autoregressive decoding. Conversely, while specialized
diffusion policies enable low-latency, parallel execution, training them from scratch typically yields narrow, single-task architectures that lack holistic visual-linguistic
reasoning. Successfully transforming pre-trained autoregressive generalists into parallel
diffusion models could combine multi-task cognitive intelligence with execution efficiency, yet this transition presents a formidable architectural challenge due to mismatched
attention patterns (causal versus bidirectional) and divergent optimization objectives. To bridge this divide, we introduce WAM-Diff2, a multi-task discrete
diffusion VLA framework powered by a three-stage hierarchical
distillation strategy. By structuring the architectural shift through progressive block-wise adaptation, block-wise
distillation, and model-wise cross-scale
distillation, WAM-Diff2 preserves the underlying semantic foundations of the base model while accelerating inference. Extensive evaluations across driving understanding, perception, and planning
benchmarks demonstrate that WAM-Diff2 effectively mitigates exposure bias and achieves performance parity with autoregressive baselines. Crucially, the autoregressive-to-
diffusion transition yields a 2.8x decoding speedup, which scales to an ultimate 15.1x acceleration when combined with system-level optimizations including FlashInfer and CUDA Graphs.
Read the full abstract ▾
All authors Zhihao Zhu, Hanlin Shang, Mingwang Xu, Feipeng Cai, Zhuolin He, Yaoyi Li, Jianhua Han, Hang Xu, Siyu Zhu
Artificial Intelligence · Cross-listed from cs.CR
CallScreenBench: Benchmarking Small Language Models as Phone Secretaries
Jiaqi Gan, Haoyuan Tang, Jamey Z. Liang et al. (+6 more)
Language models small enough to run on a handset, quantized to a few bits, are increasingly capable of acting on their user's behalf – which makes on-device task automation newly plausible. One such task is answering the phone. A phone secretary takes an unknown inbound call on its owner's behalf, and unlike the
agents most
benchmarks evaluate, it has no cooperative caller-assigned task to complete: the caller holds the goal and may be an adversary, while the secretary must begin deciding how to respond without an oracle. What matters is not task success but whether the owner would endorse how their proxy handled the call. We evaluate only the text-domain conversational decision layer;
speech recognition, audio interaction, end-to-end latency, and handset execution are outside scope. We present CallScreenBench, which reports five automated call-and-note measure groups motivated by owner endorsement. Each is paired, where available, with a counter-metric and an uncertainty estimate; no
benchmark-wide Q1-Q5 composite or leaderboard score is defined. Three guardedness diagnostics identify candidate cases for a toolless proxy that holds no credentials and calls no tools. Across three model families represented by paired 4-bit checkpoints (0.6-4B), the primary scoring snapshot gives the larger checkpoint higher point estimates on several service, recall, and plausibility measures, while triage discrimination follows a different ordering. Bare scam-side TPR rewards universal suspicion, and pairwise separation changes when legitimate-side false positives are included and across judge snapshots. Scripted degenerate
agents expose further floors, including a hangup-and-echo policy with entity recall 1.000. We report quality measures and guardedness channels separately so that a single pass/fail score does not hide their trade-offs.
Read the full abstract ▾
All authors Jiaqi Gan, Haoyuan Tang, Jamey Z. Liang, Siying Chen, Ankit Raj, Kidus Zewde, Yuchen Zhou, Yuxin Zhang, Simiao Ren
Artificial Intelligence · Cross-listed from cs.RO
VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Vision-Language-Action Robots within Wireless Sensor Networks
Dongfu Yin and Jinquan Zhang
Deploying
Vision-
Language-Action (VLA)
robots as mobile edge nodes within wireless sensor networks (WSNs) requires robust protection against physical
adversarial threats. We present VLAGuard, a framework to assess and mitigate a critical vulnerability: policy-critical action-to-
vision attention hijacking. We first introduce a stress-test module, Visuomotor
Attention-guided Semantic Attack (VASA), using printable patches to severely distract the
robot's action-conditioned cross-
attention. To counter this, we propose
Attention-Protective Fine-Tuning (APFT), a defense that stabilizes spatiotemporal
attention and enforces
geometric consistency with zero inference overhead. Evaluations across simulated and physical WSN-assisted smart environments demonstrate significant robustness gains. APFT reduces the OpenVLA failure rate from 100.0% to 25.9% in LIBERO simulations. Furthermore, across 2,000 real-world trials, APFT improves the average success rate from 23.0% to 67.4% under severe patch attacks. This highlights that protecting
attention pathways is important for improving the robustness of VLA-driven edge nodes in sensor networks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.MA
Stress-Relief Annealing: Polynomial-Time Simulation-Free Layout Optimization for Automated Warehouses
Xiangjie Luo, Yulun Zhang, Miyuki Koshimura et al. (+2 more)
We study the problem of optimizing physical layouts for automated warehouses, where hundreds to thousands of
robots are coordinated to transport packages. Previous works have shown that optimizing the warehouse layout (e.g., the physical location of the storage shelves) significantly improves throughput. However, state-of-the-art layout optimization approaches are based on evolutionary optimization methods, which treat the entire warehouse as a black box and rely on random mutation to search for high-quality layouts. While the optimization outcomes are promising, these methods require a massive number of simulations to evaluate candidate solutions, making them sample-inefficient. In this paper, we present Stress-Relief Annealing (SRA), a
polynomial-time simulation-free layout optimization
algorithm. SRA turns the task demand into a per-vertex stress field that predicts where traffic will concentrate in the warehouse; the field's peak provably caps the throughput. Our experimental results show that (1) SRA improves both the throughput and the scalability of a human-designed warehouse, roughly doubling the number of
robots it can sustain, (2) it matches or exceeds the throughput of the evolutionary baselines while taking only $19$ minutes on one CPU core, against their $25{,}000$ simulations and $25$ hours on a $64$-core machine, and (3) the gain generalizes across different Multi-
Agent Path Finding
algorithms, non-uniform task demands, and a warehouse with doubled dimensions.
Read the full abstract ▾
All authors Xiangjie Luo, Yulun Zhang, Miyuki Koshimura, Makoto Yokoo, Jiaoyang Li
Artificial Intelligence · Cross-listed from cs.LG
Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs
Chi Wang, Hanwen Wang, Yu Xia et al. (+2 more)
We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and the provable per-input query cost of recovering the clean logits. To defend against an attacker that uses returned scores for knowledge
distillation, Caliber adds independent and identically distributed Gaussian noise to the internal logits. We establish two properties of the resulting perturbed predictions. Monotone agreement degradation: When the clean logits have a unique maximizer, agreement with the clean prediction decreases strictly with the noise scale, so every target in $(1/K,1)$ corresponds to a unique positive scale; task accuracy is bounded by computable lower and upper envelopes. Per-input recovery cost: We derive a closed-form minimax lower bound on the repeated queries needed to recover the clean logits for a fixed input. Caliber normalizes noise variance by the squared median top-two logit margin and fits the resulting noise-utility relationship with a logistic curve, either per model or shared within a task. Across more than thirty model-
dataset combinations, per-model calibration achieves mean absolute relative errors of 0.6-1.4%. End-to-end experiments show that surrogate performance generally tracks the configured degradation, while fixed-input averaging follows the expected variance reduction.
Read the full abstract ▾
All authors Chi Wang, Hanwen Wang, Yu Xia, Zihan Wang, Guangdong Bai
Artificial Intelligence · Cross-listed from cs.CV
Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarking
Timothee Mickus, Claudio Savelli, Eduardo Calò et al. (+10 more)
In an age of rapid model turnover, how do we make
hallucination evaluation more perennial? We explore whether human-written
hallucination samples could take the place of model-generated
hallucinations, in order to make benchmarking detection independent of particular models. To this end, we construct a
dataset of 1,600 human-written samples, spanning four
languages (Chinese, English, French, Italian), and 18,400 samples from five
vision-and-
language models, all annotated for
hallucinations using a fine-grained span-level labeling scheme. We find that human-written samples result in higher agreement and allow greater control of
dataset contents, while remaining distributionally similar to samples derived from
vision-and-
language samples and providing a reasonable portrayal of detection capabilities - suggesting that human data is a viable substitute for model-based
hallucination benchmarks.
Read the full abstract ▾
All authors Timothee Mickus, Claudio Savelli, Eduardo Calò, Emilio Raimond, Stella Frank, Hengyu Luo, Flavio Giobergia, Vincent Segonne, Chuyuan Li, Aman Sinha, Lorenzo Vaiani, Jörg Tiedemann, Raúl Vázquez
Artificial Intelligence · Cross-listed from cs.CL
Why LLMs Give In: Conversational Factors and Reasoning Behind Medical Sycophancy
Kaike Ping, Buse Çar{\i}k, Caleb Wohn et al. (+3 more)
Large
language models can answer a medical question correctly and still abandon that answer when a user pushes back. We study this failure as medical sycophancy and ask when models are most likely to give in. Across five open-weight models, 500 MedQuAD questions, and 1.2 million trials, we use a fully crossed design over four conversational factors: user role, user evidence, interaction structure, and grounding. Medical sycophancy is nearly three times more common when users challenge an answer the model has already given than when the false claim appears in the initial query. Models are also more susceptible to users presented as physicians or medical students. Most strikingly, fabricated evidence has opposite effects across interaction structures. It increases sycophancy in single-turn interactions but reduces it after the model has already answered. Grounding helps, but does not eliminate the behavior. Sycophancy varies more across medical questions than across models, making question selection an important part of
benchmark design.
Reasoning traces suggest that multi-turn failures are associated with models turning back toward their own prior answer, while fabricated evidence receives more scrutiny after an initial response. Together, the results show that medical sycophancy depends as much on how a model is challenged and evaluated as on which model is tested.
Read the full abstract ▾
All authors Kaike Ping, Buse Çar{\i}k, Caleb Wohn, Xiaohan Ding, Tongshuai Wang, Eugenia Rho