Artificial Intelligence
I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models
Leonardo Santiago Benitez Pereira, Marcos Escudero Viñolo and Luis Herranz Arribas
Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress in generative machine unlearning, the unintended degradation of semantically related concepts that should have been retained (henceforth, interference) remains poorly characterized and inconsistently evaluated. This paper introduces I-CARE, a methodology that formalizes interference as a first-class object of study in generative unlearning. Rather than proposing a new
benchmark or unlearning
algorithm, I-CARE provides formal definitions for tasks, metrics, and templates for reporting results, enabling the systematic and reproducible study of interference across unlearning settings. While our methodology is designed to remain valid as models and unlearning
algorithms evolve, decoupling long-term scientific insight from transient empirical results, we present a feasibility demonstration with state-of-the-art
algorithms and frequently used
datasets. The results demonstrate that I-CARE enables meaningful analysis of interference patterns across multiple unlearning settings, establishing the practical applicability of the framework. The software implementation of the methodology is provided in an open-source framework, together with a web-based graphical interface that enables exploration of the outcomes of this study without requiring direct interaction with the codebase or specialized data analysis tools.
Read the full abstract ▾
Artificial Intelligence
Optimization and Constraint Modeling using LLMs with a Retrieval Augmented Generation Process
Prateek Roy and Akash Singirikonda
Both optimization modeling and constraint modeling are non-trivial problems requiring deep domain expertise and proficiency in modeling formalism
languages. Despite their importance across logistics, healthcare, and supply chain management, current large
language models regularly produce structurally inconsistent or incomplete optimization formulations, particularly in combinatorial settings. This paper evaluates whether a
Retrieval-Augmented Generation pipeline built on a curated synthetic
dataset can meaningfully improve LLM optimization modeling performance. A total of 500 optimization problems were synthesized using seed descriptions from the Text2Zinc
dataset and professional personas created using an LLM, specified in JSON and associated with validated Python solver scripts. These problems were encoded in a Chroma vector database. For each inference problem, semantically similar problems were retrieved and used as contextual guidance for a LangChain LLM
agent. Three
benchmark testbeds were used to evaluate the proposed pipeline under the Qwen 3 30B Instruct model. Accuracy rose from 40% to 72% on NL4OPT, 40% to 56% on MAMO Easy, and 32% to 56% on MAMO Complex. The use of semantically validated synthetic examples greatly improves both solution accuracy and structure. The combination of synthetic
dataset generation with
retrieval augmentation provides an effective alternative to fine-tuning, suggesting that domain-specific synthetic corpora paired with
retrieval augmentation can serve as a practical pathway for deploying LLM-based optimization tools in real-world decision-support contexts without costly model retraining.
Read the full abstract ▾
Artificial Intelligence
CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection
Qihua Pan, Zhenheng Tang, Peijie Dong et al. (+4 more)
Evaluating Large
Language Models (LLMs) incurs prohibitive computational overhead during continuous development processes. While coreset selection accelerates evaluation, existing methods either suffer from a severe “cold start” bottleneck requiring massive historical logs (e.g., Item Response Theory) or exhibit a surface lexical bias that misses the underlying
reasoning manifold of tasks. We propose CoT-Core, a novel training-free core question selection framework. Recognizing that lexically disparate questions can share equivalent underlying logic, CoT-Core
prompts LLMs to unroll zero-shot Chain-of-Thought (CoT)
reasoning trajectories. Projecting these paths into a latent space effectively clusters questions by intrinsic logical equivalence rather than superficial text similarity. Extensive experiments on GSM8K, MMLU, MMLU-Pro, and GPQA demonstrate that CoT-Core drastically reduces evaluation costs while maintaining high-fidelity score estimation, and delineate the boundary conditions of
reasoning-aware
pruning, revealing that its efficacy is intrinsically gated by task complexity.
Read the full abstract ▾
All authors Qihua Pan, Zhenheng Tang, Peijie Dong, Xiang Liu, Huacan Wang, Bo Li, Xiaowen Chu
Artificial Intelligence · Cross-listed from cs.CL
What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs
Ziran Li, Qiang Wang, Zhengyu Chen et al. (+4 more)
Choosing the right large
language model (LLM) backbone is the most consequential decision when building a
vision-
language model (VLM), yet it remains fundamentally unprincipled: compute-based scaling laws fail to generalize across model families, and no framework exists for directly predicting VLM performance before training begins. We propose the Capability-Driven
Multimodal Scaling Law, the first cross-family framework that predicts VLM
benchmark accuracy from directly observable textual capability. Given a low-dimensional capability score $S$ extracted from LLM textual
benchmarks via PCA, we model VLM performance as a function of $S$, with a per-backbone transfer rate and an absorption rate that quantifies data-scaling efficiency. To fit and validate the framework, we train over 150 VLMs on 34 LLMs spanning 7 model families under a strictly controlled recipe. Evaluations on more than 200 textual and 50
multimodal benchmarks show that the law accurately extrapolates transfer rate from models up to 8B parameters to 72B-scale backbones, predicts full VLM training trajectories with high fidelity, and generalizes to entirely held-out model families. Beyond the scaling law, our analysis surfaces actionable insights: certain textual
benchmarks negatively correlate with
multimodal performance, exposing latent
benchmark-gaming behavior; base LLMs outperform instruction-tuned counterparts as VLM backbones due to higher absorption rates and lower data-scaling decay; and different model families occupy distinct positions in the transfer–absorption space. The framework turns backbone selection from costly empirical sweeps into a principled, quantitative decision. Project website: https://wangq-dev.github.io/CDMScaling-Website ; Code: https://github.com/wangq-dev/CDMScaling ; Model weights: https://modelscope.ai/profile/wangq2k
Read the full abstract ▾
All authors Ziran Li, Qiang Wang, Zhengyu Chen, Shanglin Lei, Borun Chen, Jingang Wang, Xunliang Cai
Artificial Intelligence · Cross-listed from cs.CL
Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams
Fengxiang Wang, Qiuyang Yu, Yueying Li et al. (+14 more)
Multimodal Large
Language Models (MLLMs) are increasingly used to interpret Earth observation data, yet their capability to support real-world disaster emergency response remains insufficiently evaluated. Existing remote sensing
benchmarks largely rely on static, post-hoc, and expert-processed products, such as gridded reanalysis data, which are difficult to align with operational disaster scenarios where hazards evolve rapidly and decisions must be made under strict time constraints. To bridge this gap, we introduce Obshazard-bench, a real-time, observation-driven
benchmark for evaluating disaster intelligence in MLLMs. Unlike image-centric or post-event
benchmarks, Obshazard-bench directly integrates raw, high-frequency satellite sounding streams from diverse satellite sensors with concurrent ground-station observations, historical disaster records, and socio-economic indicators, bypassing delayed expert-processing and physical-inversion pipelines. The
benchmark covers 8 major disaster categories and 28 sub-categories across more than 60 countries, incorporating over 120 historically documented extreme-event cases and thousands of lifecycle-oriented VQA samples. Moreover, Obshazard-bench further defines a three-stage evaluation taxonomy aligned with the operational disaster workflow: Predictive Crisis Anticipation for pre-disaster risk detection and early
forecasting, Active
Evolution Reasoning for in-situ disaster tracking and termination prediction, and Multi-faceted Impact Quantification for post-disaster magnitude deduction, humanitarian burden estimation, and socio-economic impact assessment. Experiments on representative general-purpose and Earth-focused foundation models reveal substantial limitations in transforming raw multi-channel physical observations into temporally grounded and decision-relevant disaster
reasoning.
Read the full abstract ▾
All authors Fengxiang Wang, Qiuyang Yu, Yueying Li, Mingshuo Chen, Chengchi Fei, Kaiyi Xu, Lixin Gu, Wangxu Wei, Junchao Gong, Lipeng Ma, Jiong Wang, Fenghua Ling, Wenlong Zhang, Xue Yang, Wenjing Yang, Ben Fei, Long Lan
Artificial Intelligence
SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models
Jinwei Kong, Runqi Meng, Fanyi Wang et al. (+4 more)
Sparse Mixture-of-Experts (MoE) models expand foundation model capacity through conditional expert activation, but their full expert pools remain difficult to deploy under limited accelerator
memory. Although expert offloading alleviates
memory pressure by moving inactive experts to host
memory or storage, it introduces a routing-dependent transfer bottleneck: required experts are known only after native top-\(K\) routing, which serializes routing, expert loading, and expert execution during inference. To address this bottleneck, we propose SpecPrefetch, a parameter-efficient prefetching framework for offloaded MoE inference. SpecPrefetch uses a shared lightweight adapter to predict next-layer expert candidates only for asynchronous transfer, while the frozen native router still determines the final executed experts. By separating transfer prediction from execution routing, SpecPrefetch reduces exposed expert-loading latency without changing pretrained routing semantics, so prediction errors affect transfer efficiency rather than model outputs. In addition, a window-aware scheduler prioritizes feasible transfers under cache and bandwidth constraints. Across Qwen3-VL-30B-A3B and DeepSeek-VL2-Tiny, SpecPrefetch achieves the best average expert recall in 9 out of 10 model-
benchmark settings with substantially fewer trainable parameters than learned predictor baselines. On a Snapdragon 8 Elite device, SpecPrefetch further improves decoding throughput by up to \(20\%\) over a compute-optimized offloading runtime, demonstrating practical benefits for storage-constrained MoE deployment. The code and model weights are available at https://github.com/wei390/SpecPrefetch.
Read the full abstract ▾
All authors Jinwei Kong, Runqi Meng, Fanyi Wang, Wentao Qiu, Haotian Hu, Yongjian Zhou, Zhenhua Ge
Artificial Intelligence
Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models
Yijia Dai, Zhaolin Gao, Yahya Sattar et al. (+2 more)
Large
language models (LLMs) display a striking ability to predict next observations from Hidden Markov Models (HMMs) via in-context learning (ICL), but the
algorithm underlying this capability remains undetermined: prior work has proposed several candidates without consensus, and none has been grounded in the model's internal activations. We close this gap with a three-stage pipeline. First, we empirically compare LLM behavior against a suite of candidate
algorithms and narrow the space to three classes – though no single class explains LLM behavior across all HMM settings and sequence lengths. Second, we derive theoretical connections between the three classes and show how each can be implemented in-context by a
Transformer, validating the construction in a small trained
Transformer. Third, returning to pre-trained LLMs, we introduce the Principal Activations Probe (PAP), a layer-wise probing and intervention method that isolates algorithmic signals in model activations. PAP reveals low-dimensional linear representations that causally drive model predictions and track empirical ICL performance. PAP further reveals how these representations shift with properties of the underlying HMM regime; distinct computational stages are localized to different layers. Together, our results connect the in-context behavior of pre-trained LLMs to the underlying internal mechanisms and advance our understanding of how LLMs perform ICL on HMMs.
Read the full abstract ▾
All authors Yijia Dai, Zhaolin Gao, Yahya Sattar, Jennifer J. Sun, Sarah Dean
Artificial Intelligence
DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification
Mohammed Yousif, Prabhjot Singh, Arjun Pankajakshan et al. (+1 more)
Real-world document classification pipelines typically apply the same sequence of models to every incoming document, regardless of its complexity or type. This leads to inefficient use of compute and human resources: simple documents are over-processed while difficult ones may not receive enough scrutiny. We introduce DocHRL, a hierarchical reinforcement learning framework that learns to adaptively and dynamically select the most cost-effective classification policy on a per-document basis. DocHRL formulates document classification as a sequential decision problem with a two-level policy hierarchy: a top-level policy selects among broad options (
vision classifiers, LLMs, OCR, and human-in-the-loop review), while option-specific sub-policies choose the concrete model or tool to invoke. The reward signal is the negative total expected cost, which captures inference cost, cost of misclassification, and cost of human labelling. Trained with Proximal Policy Optimisation on the RVL-CDIP
benchmark, DocHRL achieves a macro F1 of 0.973 across 16 document classes while reducing average per-document cost to 2.74 normalised units compared to substantially higher costs incurred by fixed standalone classifiers. Our results demonstrate that cost-aware reinforcement learning can simultaneously improve classification performance and operational efficiency in document understanding systems.
Read the full abstract ▾
All authors Mohammed Yousif, Prabhjot Singh, Arjun Pankajakshan, Madhu Reddiboina
Artificial Intelligence
Reason Before You Retrieve: Agentic Planning for Multi-modal RAG
Tianyu Yang, Shir Simon, Zhenzhen Li et al. (+2 more)
Multimodal retrieval-augmented generation (mRAG) aims to answer image-text queries with external knowledge, but most existing systems still retrieve directly from raw
multimodal input over a flat evidence space. This design often struggles with two key challenges: the
retrieval target is under-specified because the question intent must be grounded to the correct visual referent, and the search space is weakly structured, forcing semantically distinct evidence to compete in a single global ranking step. We propose MM-R2, a
multimodal agentic
retrieval framework that reasons before
retrieval by explicitly modeling both what to retrieve and where to search. MM-R2 first constructs an intent-grounded
retrieval state from the image-question pair, capturing the information need, grounded referent, and
retrieval constraints. It then performs
retrieval over a structured KnowledgeMap, where the
agent selects relevant
retrieval units before issuing grounded queries within them. To enable this capability, we build MM-R2-Traj, a large-scale trajectory
dataset of multi-step
retrieval processes, and adopt a two-stage post-training strategy with supervised fine-tuning and GRPO. Experiments on Infoseek and Encyclopedic VQA
datasets show that MM-R2 substantially outperforms strong baselines on answer accuracy while also yielding more interpretable and verifiable
retrieval trajectories.
Read the full abstract ▾
All authors Tianyu Yang, Shir Simon, Zhenzhen Li, Minhao Cheng, Xiangliang Zhang
Artificial Intelligence
CRAFT: Learn the Schema, Execute the Plan
Aakash Kolekar, Sahika Genc, Shahriar Shariat et al. (+10 more)
Enterprise coding
agents translate natural-
language analytical requests into executable code over proprietary APIs, schemas, and metric definitions. Yet the prevailing deployment pattern injecting exhaustive schema and tool documentation into each
prompt increases inference overhead, complicates schema
evolution, and undermines reliability in multi-turn analysis. We investigate whether stable schema knowledge and tool-use behavior can instead be acquired through post-training while preserving the consistency required for production-facing analytics. We present CRAFT, a two-stage post-training recipe for schema-grounded coding
agents. First, schema-stripped PLAN supervised fine-tuning learns domain-structured plans and executable behaviors from validated trajectories without exhaustive
prompt-time schema injection. Second, execution-shaped reinforcement learning aligns the policy for tool selection, code quality, plan-code consistency, and recovery from failed executions. Training trajectories are curated through a Tri-Gate filter combining execution validation, data-integrity checks, and LLM-judge
reasoning audit. We evaluate CRAFT for planned rollout in advertising analytics, covering campaign performance analysis, metric drill-downs, entity-level performance analysis, and multi-turn analytical refinement. The enterprise evaluation environment incorporates beta APIs as the
agent-facing tool surface and spans 25 schema-linked core entities and 30 agentic workflows. Relative to a schema-stuffed baseline, CRAFT improves composite
Agent Score by +9.6 pp, consistency by +4.1 pp, and multi-turn coherence by +4.2 pp, while reducing input-
token burden by approximately 9x and schema-discovery loops by up to 5x. We further report deployment tradeoffs, reward-shaping limitations, and training-infrastructure extensions required for multi-turn tool-use reinforcement learning in enterprise settings.
Read the full abstract ▾
All authors Aakash Kolekar, Sahika Genc, Shahriar Shariat, Bunyamin Sisman, Tibor Mezi, Barbara Poblete, Shree Vandana Kachroo, Calvin Chi, Parth Parmar, Ari Singer, Prayaas Jain, Cindy Barker, Benoit Dumoulin
Artificial Intelligence · Cross-listed from cs.LG
From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language
Zachary Wojtowicz, Ayush Nayak and Jacob Andreas
The growing use of statistical learning
algorithms to infer human preferences from high-dimensional choice data runs up against a fundamental challenge: choice alternatives typically differ in many ways simultaneously, so it is generally unclear which factors actually drove an observed decision and should be credited as preferences. Compounding this problem, the opacity of these methods leaves human operators unable to inspect, contest, or correct models when they err. We introduce weights to words, a method that takes a
dataset of choice problems as input and automatically discovers a collection of domain-relevant preference dimensions, each described in natural
language and paired with a vector in the model's representational space. These dimensions address both under-determination and opacity: they can be applied to concentrate attribution on a small set of meaningful factors, and they can externalize the model's inferences in natural
language so that users can inspect and edit them in real time. We first qualitatively illustrate the method's versatility on four diverse domains: moral dilemmas, movies, wines, and free-form LLM responses. We then report two pre-registered human-subjects experiments, on moral dilemmas ($N=450$) and movie selection ($N=449$), that demonstrate its benefits for learning preference models: (1) regularizing a preference model toward the learned basis increases prediction accuracy on held-out choices, and (2) incorporating participants' structured edits further improves accuracy. In head-to-head comparisons, participants prefer the method's inferred preference profiles and endorse its predictions as more accurate.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
RouteCost: A Production-Inspired Multi-Stage Framework for Pre-Order Shipping Cost Estimation in E-Commerce
Xianling Zeng, Zihan Yu, Sichen Zhao et al. (+2 more)
Accurate pre-order shipping cost estimation is important in e-commerce because it affects price presentation, margin planning, and conversion. In practice, shipping cost is shaped not only by distance but also by destination demand mix, billable weight, dimensional pricing, surcharge triggers, and latent operational effects such as shipment consolidation. Static lookup methods therefore miss important sources of variation, while monolithic regressors may exploit strong but non-causal correlations. We propose RouteCost, a production-inspired multi-stage framework that decomposes the problem into time-aware demand
forecasting, fee-card-informed baseline pricing, Stage 2 residual correction, and proxy-based box-consolidation inference. Route-level cost estimates are aggregated through a route-weighted expectation formulation to produce product-level shipping cost predictions. Across over 250,000 orders, 260 products, and 18 months of order history, the framework improves predictive quality and aggregate calibration while preserving route-level interpretability.
Read the full abstract ▾
All authors Xianling Zeng, Zihan Yu, Sichen Zhao, Yalun Qi, Zhiming Xue
Artificial Intelligence
Feedback-Coupled Memory Systems in Continuous Time
Stefano Grassi
The Feedback-Coupled
Memory Systems (FCMS) architecture formalizes closed-loop coordination through four abstract operators, two of which - the
agent update operator $f_i$ and the environmental update operator $\Psi$ - are left axiomatically undefined in the original framework. To address this, $f_i$ is defined by Mechanism-Based Intelligence (MBI), where
agents update locally through a decentralized price mechanism and economic principles, and $\Psi$ is defined by the Coupled
Memory Graph Process (CMGP), a non-Markovian framework where the environment is treated as a physical substrate that records and responds to trajectory history coherently without external forcing. The resulting continuous-time FCMS instantiation achieves Lyapunov global dissipativity governed by the computable threshold $4\beta^2 < 2\eta\mu\gamma^2$. This generalizes both the discrete FCMS stability condition $4\eta\beta^2 < \gamma$ and CMGP's physical bifurcation threshold $\alpha_c = 1/K$, confirming that
memory dissipation must outpace feedback gain as a universal organizing principle. Numerical simulation with $N=2$
agents and mean-field validation at $N=10^6$ confirm the stability threshold and the self-reinforcing coordination cascade that emerges when it is violated.
Read the full abstract ▾
Artificial Intelligence
Closed-Loop Control with Rule-Aligned Small Language Models and Multi-Agent Self-Correction
Yuchen Wang, Javal Vyas, Tong Liu et al. (+1 more)
A key step toward autonomous industrial operation is the ability to create and reconfigure control policies from natural-
language requirement specifications, with minimal or no manual redesign. In this setting, policy generation by AI
agents can be a credible path when paired with a plant-aware validator (e.g., a digital twin) that can check generated candidate actions before execution. However, practical deployment is constrained by inference latency and compute footprint: large cloud-based models are often too slow, opaque, or data-sensitive for edge closed-loop use. This work investigates whether a compact Small
Language Model (SLM) can be retrained for control
reasoning and embedded in a validator-guided correction loop. We use a Qwen2.5-1.5B model aligned via Group Relative Policy Optimization (GRPO), combined with (i) an action
agent, (ii) a symbolic/digital-twin-style validation layer, and (iii) a reprompting
agent that iteratively steers outputs toward valid actions. In randomized thermal-control simulations (30 experiments with 500 steps each), the framework achieves 91.5% average action-
alignment accuracy (86.3%–100% across cases) at 3.84\,s mean inference latency. Under symbolic re-mapping, it maintains a 95% in-range rate, indicating robust physical regulation despite reduced
token-level agreement. These results support SLM+validator architectures as a practical path toward reconfigurable autonomous control at the edge.
Read the full abstract ▾
All authors Yuchen Wang, Javal Vyas, Tong Liu, Mehmet Mercangoz
Artificial Intelligence · Cross-listed from cs.DC
Not Every Sync Is Safe: Calibrated DiLoCo Scheduling for Shared AI Infrastructure
Maxwell Twelftree, David Lemphers, An-chi He et al. (+1 more)
DiLoCo-style training reduces communication by letting learner islands train locally before occasional outer synchronization, making it attractive for fragmented industrial AI fleets where training shares hardware with latency-sensitive serving. The question for such fleets is when an outer merge is worth its system cost, and whether choosing which windows to defer matters at all. Existing scheduling studies evaluate workload-aware policies against fixed-period baselines, but most omit the control that isolates timing from budget: matched random deferral, which inherits the controller's synchronization budget but is not itself deployable. This omission is consequential: across controlled stress tests and real vLLM sidecar replays, matched random ties or beats every forecast-free policy we test, so gains reported against weaker baselines cannot be attributed to window choice. We fill this gap with Workload-Aware DiLoCo (WA-DiLoCo), a score-based controller that weighs learner progress against fleet pressure, and a calibration protocol that determines when matched random can be beaten, then demonstrate that it can. In the bursty regime where calibration exposes request-overlap structure, adding a one-step EWMA burst forecast to the online controller beats matched random in real vLLM sidecar replay, reducing SLO violations from 6.54% to 5.09% (8 of 10 seeds, $p=0.021$); offline Calibrated-WA, a non-deployable bound, shows the remaining headroom at 4.45% versus 6.26%. The deployable lesson remains the protocol: report real-sidecar effect-size transfer, a no-sync load match, and a matched-random envelope before claiming serving-SLO improvement.
Read the full abstract ▾
All authors Maxwell Twelftree, David Lemphers, An-chi He, Yue Yang
Artificial Intelligence
iFLYTEK-Embodied-Omni Technical Report
Yuan Zhang, Jingfei Ni, Guanchen Lu et al. (+12 more)
General-purpose
embodied agents must understand
multimodal instructions, anticipate how their environment will evolve, and produce precise control actions over extended horizons. Existing approaches typically specialize in visual-
language reasoning,
video-based world modeling, or action generation, while cascaded pipelines that first synthesize future observations and then infer actions can introduce interface bottlenecks and compound prediction errors. We present iFLYTEK-
Embodied-Omni, a unified
multimodal foundation model that jointly models
vision(
videos and images),
language, and action within a single Omni framework. Its modality-specific visual-
language,
video-generation, and action-generation components communicate through shared
multimodal self-
attention. This design establishes
brain-cerebellum collaboration: the
vision-
language modeland
video generation model form a high-level
brain for instruction understanding, task planning, progress tracking, and future visual-state prediction, whereas the action generation modelserves as a low-level cerebellum that directly converts planned subgoals and shared
multimodal context into executable action chunks. To develop these capabilities, we combine action-annotated and action-free
embodied videos from human demonstrations and
robot interactions with
embodied reasoning,
embodied perception, and general-purpose image-text data to construct a comprehensive
dataset. We further adopt a four-stage strategy that progressively trains the VLM, VGM, and AGM before jointly fine-tuning the complete model.
Read the full abstract ▾
All authors Yuan Zhang, Jingfei Ni, Guanchen Lu, Shiqi Zhang, Qingshan Xu, Chi Liu, Xin Nie, Wenjie Xu, Lin Gao, Zhiyuan Cheng, Mingxin Zhou, Jiajia Wu, Diyuan Liu, Jia Pan, Chao Ji
Artificial Intelligence · Cross-listed from cs.CY
Financing Artificial Intelligence Infrastructure: Mapping AI Infrastructure Investment and Compute Governance Across Africa
Kai-Hsin Hung, Sumaya Nur Adan, Krupa Suchak et al. (+3 more)
Artificial intelligence depends on large-scale compute resources and their supporting infrastructure. However, AI governance debates treat compute primarily as a technical input rather than as an outcome of investment, ownership, and financial control. This paper examines AI infrastructure investment flows across Africa through a systematic analysis of 46 publicly announced projects totalling USD $12.7 billion between 2019 and 2025. Using a value chain framework, we analyze who invests in AI-relevant infrastructure and where investments concentrate. Our findings reveal a highly concentrated landscape dominated by global data center operators, hyperscale technology firms, and development finance institutions, clustering in South Africa, Kenya, Nigeria, and Egypt. We introduce asymmetrical interdependence to describe a structural condition in which capital and physical infrastructure account for 73% of total funding while control remains concentrated in the compute layer among a small number of global technology firms. We argue that compute governance must account for capital flows, ownership, and control, not only geographic access, because these dynamics shape AI compute equity. Infrastructure presence is necessary but insufficient for meaningful governance capacity.
Read the full abstract ▾
All authors Kai-Hsin Hung, Sumaya Nur Adan, Krupa Suchak, Armita Sadeghian Barzoki, Kofi Yeboah, Mohammad Amir Anwar
Artificial Intelligence · Cross-listed from cs.SE
Reinforcement Learning for Software Vulnerability Analysis: A Systematic Review with Emphasis on C/C++ Source Code and Static Analysis
Bruno Caro-Vásquez, Carola Figueroa-Flores and Gastón Marquez
Vulnerability detection in C/C++ software remains a major security challenge due to code complexity, manual
memory management, and the limitations of traditional static analysis. Reinforcement Learning (RL) has emerged as a promising approach, particularly for fuzzing, test generation, program exploration, and, more recently, vulnerability detection and localization. Following PRISMA 2020 guidelines, this work reviews RL techniques for software vulnerability analysis, focusing on C/C++ source code and static analysis. We identified 21 primary studies published between 2015 and 2026 from major scientific databases and complementary searches. We analyze the addressed tasks,
algorithms, state-action-reward-environment formulations, code representations,
datasets, and evaluation metrics. Results show that 15 studies focus on fuzzing and guided exploration, only 3 on direct vulnerability detection, and just 1 on statement-level localization. Moreover, statically extracted structural representations such as Control Flow Graphs (CFGs) and Abstract Syntax Trees (ASTs) are rarely used as
agent states, and
benchmarks lack comparability. We propose a task- and formulation-oriented taxonomy and identify a key research gap: the absence of RL
agents that use source-code CFGs as states to detect and localize vulnerable nodes.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Shaoxuan Li, Xiangyu Dong, Xiaoguang Ma et al. (+3 more)
Vision-
language navigation (VLN) has recently advanced with large
language and
multimodal models, enabling
agents to follow natural-
language instructions in unseen environments without training a task-specific
navigation policy. However, most existing VLN methods relying on large models still adopt an open-loop decision-execution approach, where candidate actions are generated from instructions and observations but are rarely verified or corrected before execution. This causes critical issues in aerial VLN, where minor errors in intermediate actions may quickly accumulate into large trajectory deviations and lead to target loss. To address this issue, we propose Closed-loop Self-verified
Retrieval-augmented
Reasoning (CLOSER), a training-policy-free method that sequentially performs action
reasoning, reliability verification, targeted
retrieval, and action correction in a closed-loop manner before executing concrete actions. We instantiate the CLOSER in aerial VLN tasks and develop a CLOSER-VLN framework, which is composed of three components: a hierarchical reasoner for generating candidate actions based on available information, a multidimensional action verifier for assessing the reliability of actions generated by the reasoner, and a verification-triggered
multimodal retriever for retrieving targeted exemplars from a
memory bank only when verification fails. We conduct experimental evaluations on the CityNav
benchmark, where CLOSER-VLN achieves 32.01% SR and 21.28% SPL on the test-unseen split, confirming the effectiveness of closed-loop
reasoning.
Read the full abstract ▾
All authors Shaoxuan Li, Xiangyu Dong, Xiaoguang Ma, Junfeng Chen, Haoran Zhao, Yaoming Zhou
Artificial Intelligence · Cross-listed from cs.MA
SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game
Yeqi Feng, Yuxin Chen and Tianxing He
Evaluating LLM
agents requires dynamic environments that go beyond static
reasoning and zero-sum games. Real-world economic interaction is often open-ended and mixed-motive:
agents must negotiate, create positive-sum surplus, compete for scarce assets, and plan under delayed returns. We introduce SidConArena, a new
benchmark framework for evaluating LLM
agents in open-ended, positive-sum bargaining. SidConArena formalizes a multi-player economy as a finite-horizon partially observable
stochastic game with three coupled phases: natural-
language negotiation with binding trades, deterministic converter-based production, and sealed-bid auctions for long-term assets. The framework combines structured observations, phase-aware
agent dispatching, a neural-symbolic action interface, and asynchronous execution, enabling free-form interaction while preserving rule-grounded evaluation. Across homogeneous and heterogeneous tournaments, stronger frontier models achieve higher economic outcomes, yet
agents still misvalue resources, bargain passively, and remain limited in long-horizon investment planning.
Read the full abstract ▾
Artificial Intelligence
auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation
Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft et al. (+4 more)
AI-based scientific automation is increasingly possible by using
agents to generate hypotheses, design experiments, and analyze data. Data collection is a major bottleneck in this pipeline, however. Psychology, and computational cognitive science in particular, is well-positioned to benefit from AI experimentation because theories are often represented as code and crowdsourcing platforms enable programmatic human data collection at scale. Here, we apply automated discovery techniques to the project of generating theories in computational cognitive science, with an
agent-based system collecting human data independently through crowdsourced survey experiments. As a testbed, we use a classic case study from cognitive psychology: judging which sequences of coin flips seem subjectively more random. Our system, auto-psych, uses nested
agent-based discovery loops to generate explanatory theories of human behavior. The inner loop
conjectures, fits, and critiques probabilistic cognitive models; the outer loop designs experiments to test these models, launches them online, and analyzes the data. This system can quickly and reliably recover ground-truth theories from synthetic data via systematic experimentation, but the nested structure is critical to model performance. Further, in three independent sequences of human experiments, the system finds theories that fit the data better than theories generated from the scientific literature. This work thus demonstrates the feasibility of automated data collection and theory discovery in computational cognitive science.
Read the full abstract ▾
All authors Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft, Linas Nasvytis, Michael Y. Li, Noah D. Goodman, Michael C. Frank
Artificial Intelligence
MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation
Xiaochen Wang, Bao Hoang, Han Liu et al. (+2 more)
Retrieval-augmented generation (RAG) over knowledge graphs has emerged as a promising approach for grounding large
language models, yet existing
benchmarks largely overlook the challenges of
retrieval in
multimodal knowledge graph RAG (MKG-RAG). In practice,
retrieval is a critical bottleneck:
multimodal knowledge is heterogeneous, difficult to align across modalities, and often poorly served by retrievers designed for unstructured corpora. To address this gap, we introduce MKG-RAG-Bench, a cross-domain
benchmark explicitly designed to evaluate
retrieval in MKG-RAG. MKG-RAG-Bench is constructed from two
multimodal knowledge graphs spanning general and medical domains, and includes carefully aligned question-answering
datasets that support controlled evaluation of both
retrieval and downstream generation. The
benchmark is built using an LLM-based curation pipeline that filters low-utility knowledge, generates structurally grounded queries with exact supervision, and systematically covers diverse modality configurations. Through extensive experiments across representative retriever families and modality settings, we show that effective
multimodal retrieval remains challenging yet crucial for end-to-end MKG-RAG performance, and that
retrieval quality strongly determines generation outcomes. By isolating
retrieval as a first-class evaluation target, MKG-RAG-Bench provides a principled foundation for diagnosing current limitations and advancing
multimodal knowledge graph RAG systems.
Read the full abstract ▾
All authors Xiaochen Wang, Bao Hoang, Han Liu, Ting Wang, Fenglong Ma
Artificial Intelligence · Cross-listed from cs.CV
Active Adversarial Perturbation-driven Associative Memory Retrieval for RGB-Event Visual Object Tracking
Xiao Wang, Xufeng Lou, Zikang Yan et al. (+5 more)
RGB-Event tracking improves localization robustness by fusing RGB appearance textures and dense temporal motion cues from event sensors. While this multi-modal scheme broadens tracking applicability, real-world scenes suffer diverse structured signal degradations that hinder traditional multi-modal fusion. In harsh environments, either modality can lose reliability drastically, and targets frequently appear incomplete due to occlusion, edge truncation and foreground clutter.To tackle the above challenges, we present a hierarchical perturbation and
retrieval framework tailored for RGB-Event tracking with robustness against partial target missing and modal degradation, termed APRTrack. To mimic real-world signal corruption, APRTrack constructs structured degradation via two
adversarial perturbation branches at the modality and spatial levels, which separately simulate full-modal failure and localized target region absence. A hierarchical routing mechanism is designed to disentangle the training pipelines of the two perturbation types, effectively eliminating feature collapse induced by superimposed degradation constraints. Furthermore, we devise Footprint-guided Channel-calibrated Hopfield
Retrieval (FCHR) for reliable historical information compensation. This module evaluates
retrieval confidence based on association footprints between queries and
memory banks, and calibrates the
retrieval metric space prior to Hopfield matching, realizing controllable historical feature compensation bounded to target regions. Extensive experiments on FE108, COESOT, VisEvent, and FELT
datasets demonstrate the effectiveness of our proposed strategies for the RGB-Event visual object tracking. The source code and pre-trained models will be released on https://github.com/Event-AHU/OpenEvTracking
Read the full abstract ▾
All authors Xiao Wang, Xufeng Lou, Zikang Yan, Lan Chen, Sibao Chen, Yaowei Wang, Yonghong Tian, Jin Tang
Artificial Intelligence
Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning – The Limit of the Scaling Law
Tiansi Dong, Mateja Jamnik and Pietro Liò
By promoting vectors to spheres and enabling explicit model construction, neural networks can perform symbolic-level syllogistic
reasoning without training data. We identify two fundamental limitations that prevent conventional data-driven machine learning systems from achieving this capability: training data generated by the combination table cannot distinguish all 24 valid syllogism types, and end-to-end premise-to-conclusion mapping creates contradictory targets within neural components. Experiments with two representative conventional systems, GPT-5 using linguistic inputs and Euler Net using visual inputs, support this analysis. ChatGPT GPT-5 may reach 100% accuracy in syllogistic
reasoning, but with
hallucinations. Because the learning process terminates upon reaching 100% accuracy, the system cannot progress beyond empirical accuracy to symbolic level
reasoning. Random test data reduced Euler Net's accuracy to 56%. Repeatedly expanding the training set increased its accuracy to 97%, with perfect performance on 8 syllogism types. However, because unintended inputs cannot be exhaustively covered, even 100% test accuracy does not imply symbolic-level
reasoning. Since syllogistic
reasoning underpins logical
reasoning and human rationality, these results suggest that increasing data and training time alone cannot ensure symbolic level logical
reasoning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
ProvenAI: Provenance-Native Traces of Evidence in Generated Answers
Mohammad Faizan and Dalal Alharthi
Retrieval-augmented systems routinely present citations alongside generated answers, yet a citation does not confirm that the corresponding source meaningfully shaped the output. This paper introduces ProvenAI, a framework that decomposes transparency in multi-hop question answering into three independently measurable layers: answer correctness, citation fidelity against
benchmark supporting evidence, and per-document influence under leave-one-resource-out intervention. Targeting the HotpotQA distractor
benchmark through a seven-stage pipeline covering data normalisation,
retrieval indexing, citation-aware answer generation, attribution
auditing, ablation-based influence estimation, batch evaluation, and interactive inspection, ProvenAI evaluates 7,405 validation examples drawn from a canonical corpus of 509,300 passages. The system achieves 53.53% answer accuracy alongside a mean citation-fidelity score of 71.55%, and a worked example surfaces what we call the citation-influence gap: a clean citation audit co-occurring with a profile in which one cited source registers only weak influence while seven uncited sources demonstrably shift the output. We formalise the relationship between the implemented surface proxy and a
token-level KL-divergence target through a stated faithfulness condition, ground the framework in causal-mediation analysis and database-provenance theory, and discuss how the three measurement layers compose with cryptographic provenance architectures emerging in autonomous scientific discovery. ProvenAI establishes that meaningful transparency in
retrieval-grounded QA requires traceable links across retrieved, cited, and behaviourally influential evidence as three distinct, independently measured layers.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from q-bio.NC
Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist
Akshay K. Jagadish, Younes Strittmatter, Nori Jacoby et al. (+5 more)
Across the sciences, autonomous systems are increasingly being used in closed-loop discovery, proposing new theories and designing and running experiments to test them. This approach is yet to be applied in the field of cognitive science, where the central bottleneck is theory-building: the creative step of turning the accumulated failures of existing models into better ones. Theory generation has remained manual even as data collection, modeling, and experiment design have been automated. We present the Automated Cognitive Scientist (AutoCog), a fully autonomous agentic-AI system that closes this loop. Large-
language-model
agents advocate competing theories, each expressed as an executable cognitive model, design experiments that best discriminate them, collect behavioral data from participants recruited online, score theories against collected data based on their generative performance, diagnose why they fail, and synthesize a better successor. Repeating this cycle allows them to search the space of theories, models, and experiments. In the domain of decision-making, AutoCog recovered known decision-making strategies from simulated behavior, including unconventional ones, showing that its discoveries are ultimately driven by the data rather than strictly bound by the priors of the underlying
language models. When run with human participants, it produced theories that outperformed the established theories it was seeded with and generalized to held-out studies in two different experimental settings. It also surfaced a novel theory of multi-cue decision-making in which choices show diminishing sensitivity to feature values. The distinctive predictions of this theory were confirmed in a preregistered study with new participants. AutoCog demonstrates how an automated discovery system can be used to turn cognitive theory-building into an explicit, executable, and cumulative science.
Read the full abstract ▾
All authors Akshay K. Jagadish, Younes Strittmatter, Nori Jacoby, George Kachergis, Eric Schulz, Nathaniel Daw, Suyog H. Chandramouli, Thomas L. Griffiths
Artificial Intelligence · Cross-listed from cs.RO
WatchAct: A Benchmark for Behavior-Grounded Robot Manipulation
Baiqi Li, Ce Zhang, Yu Fang et al. (+4 more)
A
robot working alongside people must reason about what they have done, in what order, and with what intent.
Video carries the spatial layouts, object histories, and gestures that
language leaves underspecified, yet today's manipulation
benchmarks pair an instruction with a single current image, offering no way to evaluate
reasoning over observed human behavior. We introduce WatchAct, a
benchmark for
robot manipulation grounded in observed human behavior. Each instance pairs a real-world human-action
video and a
language instruction with an aligned simulator scene and an executable LIBERO task, enabling scalable and reproducible evaluation. WatchAct comprises 3,000 long-horizon instances across 14 tasks in four capability domains drawn from the cognitive demands of watching another
agent: parsing events (Event Grounding), recovering procedural structure (Procedural
Reasoning), inferring unstated intent (Implicit Intent Inference), and tracking how the scene was changed (Episodic
Reasoning). We further propose a disentangled evaluation protocol that separately measures (i)~
video-to-plan
reasoning by
vision-
language models, (ii)~policy execution under oracle plans, and (iii)~full task completion by integrated planner–policy pipelines. In both simulation and on a Franka Research 3
robot, current systems remain far from solving WatchAct. The best pipeline, Gemini-3.1-Pro with $\pi_{0.5}$, reaches only 16.3% Success Rate (SR) in simulation and 14.0% on the real
robot. Gemini-3.1-Pro attains just 36.8% Plan SR (vs. 97.1% for humans), while $\pi_{0.5}$ reaches only 21.5% Task SR under oracle plans and drops to 10.6% on out-of-domain scenarios.
Dataset and code are available at https://baiqi-li.github.io/watchact_page/.
Read the full abstract ▾
All authors Baiqi Li, Ce Zhang, Yu Fang, Yue Yang, Shangzhe Li, Mingyu Ding, Gedas Bertasius
Artificial Intelligence · Cross-listed from cs.LO
AXLE: A Cloud Infrastructure for Lean 4 Theorem Proving Utilities
Jimmy Xin, Alex Schneidman, Chris Cummins et al. (+3 more)
We present AXLE (Axiom Lean Engine), a cloud service for Lean 4 proof manipulation, extraction, and verification. Recent progress in AI for mathematics – reinforcement learning pipelines, agentic proving workflows,
dataset curation – demands Lean 4 tooling that scales to millions of requests while remaining correct and robust; existing infrastructure offers parallel compilation but not scalable proof verification, higher-level proof manipulation, multi-version support, or per-request isolation at the throughput modern AI workflows require. AXLE provides 14 Lean 4 metaprogramming tools spanning strict proof verification, declaration metadata extraction, semantic source manipulation, deterministic proof repair and simplification, and lemma extraction. The service runs as a multi-tenant cloud deployment with per-request isolation and concurrent support for multiple Lean 4 and Mathlib versions, accessible via a Python SDK, command-line interface, web UI, MCP server, and raw HTTP API. AXLE is publicly available and free to use at https://axle.axiommath.ai and via the axiom-axle PyPI package, with no local Lean 4 installation required. It has served over 500 million requests to date and is the underlying infrastructure for Axiom Math's proving efforts, including its 12/12 score on the 2025 Putnam competition.
Read the full abstract ▾
All authors Jimmy Xin, Alex Schneidman, Chris Cummins, Karun Ram, Srihari Ganesh, Jannis Limperg
Artificial Intelligence · Cross-listed from cs.CL
ConflictScore: Identifying and Measuring How Language Models Handle Conflicting Evidence
Siyi Liu, Aaron Halfaker, Dan Roth et al. (+1 more)
Existing metrics for factuality and faithfulness evaluate whether an answer is supported or contradicted by its grounding documents, but they fail to capture when both supporting and contradicting evidence coexist. We introduce ConflictScore, a novel metric that quantifies how well a model's response acknowledges conflicting evidence in its grounding documents. Our framework decomposes responses into atomic claims, labels each claim against each grounding document, and then aggregates these labels into two complementary measures: ConflictScore-Count (CS-C), the proportion of claims exhibiting conflicts, and ConflictScore-Ratio (CS-R), the balance between supporting and contradicting evidence. We develop ConflictBench, a
benchmark covering diverse forms of conflicts such as ambiguity, contradiction, and divergent opinions, to systematically evaluate our metric. Experiments show that ConflictScore effectively detects overconfident claims across domains and can serve as a corrective feedback mechanism that improves truthfulness on TruthfulQA.
Read the full abstract ▾
All authors Siyi Liu, Aaron Halfaker, Dan Roth, Patrick Xia
Artificial Intelligence · Cross-listed from cs.RO
Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?
Tyler Ga Wei Lum, Kushal Kedia, C. Karen Liu et al. (+1 more)
Multi-fingered
robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach. These tasks are contact-rich, making data collection for imitation learning difficult, and sparse-reward, making direct exploration with reinforcement learning (RL) intractable. Consequently, prior work has made progress by structuring the problem with specialized grippers, tool attachments, and environment fixtures. In this work, we argue that before a
robot can perfect precise assembly, it must first learn to play. We further ask the question: what factors in the process of learning to play matter for precise assembly? We propose Play2Perfect, an RL framework for task-agnostic pretraining through play on diverse objects and goals, which is then perfected on precise assembly. The goal of play is to acquire reusable manipulation priors, such as grasping, in-hand reorientation and pose reaching. Finetuning then adapts this general prior to assembly, focusing exploration on the final contact-rich, high-precision interactions needed for success. We systematically study key design choices in play pretraining, including object diversity, training objective, trajectory diversity, and goal precision. We show that our prior is 33x more sample-efficient than RL training from scratch, even when provided with dense, multi-stage rewards. We demonstrate zero-shot sim-to-real transfer, achieving 60% success on tight insertions with only 0.5 mm contact clearance, and over 50% success on long-horizon multi-part assembly and screwing.
Read the full abstract ▾
All authors Tyler Ga Wei Lum, Kushal Kedia, C. Karen Liu, Jeannette Bohg