# Research Papers — 2025-10 · bundle page 125 of 217

> Full-text markdown of papers #6201–6250 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/125
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/124.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/126.md)

### BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing

Authors: Caelin Kaplan, Alexander Warnecke, Neil Archibald
Published: 2025-10-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.11823v1

AI models are being increasingly integrated into real-world systems, raising significant concerns about their safety and security. Consequently, AI red teaming has become essential for organizations to proactively identify and address vulnerabilities before they can be exploited by adversaries. While numerous AI red teaming tools currently exist, practitioners face challenges in selecting the most appropriate tools from a rapidly expanding landscape, as well as managing complex and frequently conflicting software dependencies across isolated projects. Given these challenges and the relatively small number of organizations with dedicated AI red teams, there is a strong need to lower barriers to entry and establish a standardized environment that simplifies the setup and execution of comprehensive AI model assessments. Inspired by Kali Linux's role in traditional penetration testing, we introduce BlackIce, an open-source containerized toolkit designed for red teaming Large Language Models (LLMs) and classical machine learning (ML) models. BlackIce provides a reproducible, version-pinned Docker image that bundles 14 carefully selected open-source tools for Responsible AI and Security testing, all accessible via a unified command-line interface. With this setup, initiating red team assessments is as straightforward as launching a container, either locally or using a cloud platform. Additionally, the image's modular architecture facilitates community-driven extensions, allowing users to easily adapt or expand the toolkit as new threats emerge. In this paper, we describe the architecture of the container image, the process used for selecting tools, and the types of evaluations they support.

---

### Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations

Authors: Suryaansh Jain, Umair Z. Ahmed, Shubham Sahai, Ben Leong
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11822v2

New Large Language Models (LLMs) become available every few weeks, and modern application developers confronted with the unenviable task of having to decide if they should switch to a new model. While human evaluation remains the gold standard, it is costly and unscalable. The state-of-the-art approach is to use LLMs as evaluators ( LLM-as-a-judge), but this suffers from a critical flaw: LLMs exhibit a strong positive bias. We provide empirical evidence showing that while LLMs can identify valid outputs with high accuracy (i.e., True Positive Rate 96%), they are remarkably poor at identifying invalid ones (i.e., True Negative Rate <25%). This systematic bias, coupled with class imbalance, often leads to inflated reliability scores. While ensemble-based methods like majority voting can help, we show that they are not good enough. We introduce an optimal minority-veto strategy that is resilient to missing data and mitigates this bias to a large extent. For scenarios requiring even higher precision, we propose a novel regression-based framework that directly models the validator bias using a small set of human-annotated ground truth data. On a challenging code feedback task over 366 high-school Python programs, our regression approach reduces the maximum absolute error to just 1.2%, achieving a 2x improvement over the best-performing ensemble of 14 state-of-the-art LLMs.

---

### Enhancing the Quality of 3D Lunar Maps Using JAXA's Kaguya Imagery

Authors: Yumi Iwashita, Haakon Moe, Yang Cheng, Adnan Ansar, Georgios Georgakis, Adrian Stoica, Kazuto Nakashima, Ryo Kurazume, Jim Torresen
Published: 2025-10-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.11817v1

As global efforts to explore the Moon intensify, the need for high-quality 3D lunar maps becomes increasingly critical-particularly for long-distance missions such as NASA's Endurance mission concept, in which a rover aims to traverse 2,000 km across the South Pole-Aitken basin. Kaguya TC (Terrain Camera) images, though globally available at 10 m/pixel, suffer from altitude inaccuracies caused by stereo matching errors and JPEG-based compression artifacts. This paper presents a method to improve the quality of 3D maps generated from Kaguya TC images, focusing on mitigating the effects of compression-induced noise in disparity maps. We analyze the compression behavior of Kaguya TC imagery, and identify systematic disparity noise patterns, especially in darker regions. In this paper, we propose an approach to enhance 3D map quality by reducing residual noise in disparity images derived from compressed images. Our experimental results show that the proposed approach effectively reduces elevation noise, enhancing the safety and reliability of terrain data for future lunar missions.

---

### Task-Aware Reduction for Scalable LLM-Database Systems

Authors: Marcus Emmanuel Barnes, Taher A. Ghaleb, Safwat Hassan
Published: 2025-10-13
Categories: cs.SE, cs.CL, cs.DB
arXiv: https://arxiv.org/abs/2510.11813v1

Large Language Models (LLMs) are increasingly applied to data-intensive workflows, from database querying to developer observability. Yet the effectiveness of these systems is constrained by the volume, verbosity, and noise of real-world text-rich data such as logs, telemetry, and monitoring streams. Feeding such data directly into LLMs is costly, environmentally unsustainable, and often misaligned with task objectives. Parallel efforts in LLM efficiency have focused on model- or architecture-level optimizations, but the challenge of reducing upstream input verbosity remains underexplored. In this paper, we argue for treating the token budget of an LLM as an attention budget and elevating task-aware text reduction as a first-class design principle for language -- data systems. We position input-side reduction not as compression, but as attention allocation: prioritizing information most relevant to downstream tasks. We outline open research challenges for building benchmarks, designing adaptive reduction pipelines, and integrating token-budget--aware preprocessing into database and retrieval systems. Our vision is to channel scarce attention resources toward meaningful signals in noisy, data-intensive workflows, enabling scalable, accurate, and sustainable LLM--data integration.

---

### PHANTOM RECALL: When Familiar Puzzles Fool Smart Models

Authors: Souradeep Mukhopadhyay, Rishabh Baral, Nimeesh Mahajan, Samhitha Harish, Aswin RRV, Mihir Parmar, Mutsumi Nakamura, Chitta Baral
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.11812v1

Large language models (LLMs) such as GPT, Gemini, and Claude often appear adept at solving classic logic puzzles--but how much genuine reasoning underlies their answers? Recent evidence suggests that these models frequently rely on memorized templates rather than reasoning from first principles. When puzzles are slightly modified, their performance collapses, revealing a striking fragility. In particular, we asked: Have LLMs addressed these issues? To what extent? How about perturbations to other puzzles? Is there a general way of reformulating the prompt so that the models do better? To examine these things systematically, we introduce PHANTOM RECALL, a benchmark comprising 25 well-known logic puzzles and 149 carefully designed perturbations that preserve reasoning structure but alter superficial details and solutions. We evaluate eleven leading LLMs and identify a recurring failure mode--phantom recall--where models confidently reproduce memorized solutions or spurious rationales that no longer fit the altered scenario. To probe and mitigate this issue, we contribute three tools: (i) an automated logical-equivalence judge to detect reasoning mismatches, (ii) a taxonomy of fine-grained reasoning error categories, and (iii) a prompting-based mitigation framework guided by these categories. Despite near-perfect accuracy on unmodified puzzles, models significantly underperform humans on perturbed ones, exhibiting both phantom recall and over-elaboration. Our findings reveal a crucial limitation: LLMs often fail to re-reason when contextual cues shift--highlighting the gap between linguistic fluency and logical understanding.

---

### On Thompson Sampling and Bilateral Uncertainty in Additive Bayesian Optimization

Authors: Nathan Wycoff
Published: 2025-10-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.11792v1

In Bayesian Optimization (BO), additive assumptions can mitigate the twin difficulties of modeling and searching a complex function in high dimension. However, common acquisition functions, like the Additive Lower Confidence Bound, ignore pairwise covariances between dimensions, which we'll call \textit{bilateral uncertainty} (BU), imposing a second layer of approximations. While theoretical results indicate that asymptotically not much is lost in doing so, little is known about the practical effects of this assumption in small budgets. In this article, we show that by exploiting conditional independence, Thompson Sampling respecting BU can be efficiently conducted. We use this fact to execute an empirical investigation into the loss incurred by ignoring BU, finding that the additive approximation to Thompson Sampling does indeed have, on balance, worse performance than the exact method, but that this difference is of little practical significance. This buttresses the theoretical understanding and suggests that the BU-ignoring approximation is sufficient for BO in practice, even in the non-asymptotic regime.

---

### Minimax Rates for Learning Pairwise Interactions in Attention-Style Models

Authors: Shai Zucker, Xiong Wang, Fei Lu, Inbar Seroussi
Published: 2025-10-13
Categories: stat.ML, cs.LG, math.PR, math.ST
arXiv: https://arxiv.org/abs/2510.11789v2

We study the convergence rate of learning pairwise interactions in single-layer attention-style models, where tokens interact through a weight matrix and a nonlinear activation function. We prove that the minimax rate is $M^{-\frac{2β}{2β+1}}$, where $M$ is the sample size and $β$ is the Hölder smoothness of the activation function. Importantly, this rate is independent of the embedding dimension $d$, the number of tokens $N$, and the rank $r$ of the weight matrix, provided that $rd \le (M/\log M)^{\frac{1}{2β+1}}$. These results highlight a fundamental statistical efficiency of attention-style models, even when the weight matrix and activation are not separately identifiable, and provide a theoretical understanding of attention mechanisms and guidance on training.

---

### GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving

Authors: Ruida Wang, Jiarui Yao, Rui Pan, Shizhe Diao, Tong Zhang
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11769v2

Solving math problems through verifiable languages such as Lean has significantly impacted both the mathematics and computer science communities. Current state-of-the-art models are often trained with expensive online Reinforcement Learning (RL) or expert iteration. However, these approaches rely on fixed problem sets, which causes inefficient training and limits the model to tackle complex problems. To overcome these limitations, we propose **GAR**: *Generative Adversarial Reinforcement learning*, a comprehensive RL training framework that jointly trains the problem composer and solver in an adversarial loop. **GAR** introduces an implicit curriculum learning mechanism, which aligns task difficulty with the prover's evolving capability. It thereby improves the training efficiency and enables stronger performance of proving advanced theorems. Experiments show that with **GAR** training, Goedel-Prover-V2-8B and DeepSeek-Prover-V2-7B achieve an average relative improvement in pass@32 of **4.20%** on MiniF2F-Test benchmark, while DeepSeek-Prover-V2's pass@32 on ProofNet-Test increases from 22.58% to **25.81%**. Beyond formal proving, **GAR** establishes a general RL paradigm for co-evolution of problem generation and solving under verifiable environments. The training code for this paper is open-sourced in https://github.com/RickySkywalker/GAR-Official

---

### Audio-Guided Visual Perception for Audio-Visual Navigation

Authors: Yi Wang, Yinfeng Yu, Fuchun Sun, Liejun Wang, Wendong Zheng
Published: 2025-10-13
Categories: cs.SD, cs.AI, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.11760v1

Audio-Visual Embodied Navigation aims to enable agents to autonomously navigate to sound sources in unknown 3D environments using auditory cues. While current AVN methods excel on in-distribution sound sources, they exhibit poor cross-source generalization: navigation success rates plummet and search paths become excessively long when agents encounter unheard sounds or unseen environments. This limitation stems from the lack of explicit alignment mechanisms between auditory signals and corresponding visual regions. Policies tend to memorize spurious \enquote{acoustic fingerprint-scenario} correlations during training, leading to blind exploration when exposed to novel sound sources. To address this, we propose the AGVP framework, which transforms sound from policy-memorable acoustic fingerprint cues into spatial guidance. The framework first extracts global auditory context via audio self-attention, then uses this context as queries to guide visual feature attention, highlighting sound-source-related regions at the feature level. Subsequent temporal modeling and policy optimization are then performed. This design, centered on interpretable cross-modal alignment and region reweighting, reduces dependency on specific acoustic fingerprints. Experimental results demonstrate that AGVP improves both navigation efficiency and robustness while achieving superior cross-scenario generalization on previously unheard sounds.

---

### AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework

Authors: Hongyu Lin, Haolin Pan, Haoran Luo, Yuchen Li, Kaichun Yao, Libo Zhang, Mingjie Xing, Yanjun Wu
Published: 2025-10-13
Categories: cs.PL, cs.AI
arXiv: https://arxiv.org/abs/2510.11759v1

Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software optimization, automating compiler optimization remains challenging due to: (1) semantic misalignment between abstract program representations and concrete optimization passes, (2) inefficient interaction mechanisms between agents and compiler environments, and (3) reward sparsity from the extensive decision-making process within large optimization spaces. This paper introduces \textbf{AwareCompiler}, an agentic framework for compiler optimization that addresses these challenges through three key innovations: structured knowledge integration and dataset construction, knowledge-driven adaptive pass generation, and data-driven hybrid training pipeline. Experimental results on standard benchmarks demonstrate that AwareCompiler significantly outperforms existing baselines in both performance and efficiency, highlighting the effectiveness of our synergistic knowledge-data-driven approach. Our code is publicly available at https://github.com/LHY-24/AwareCompiler.

---

### The Adoption Paradox for Veterinary Professionals in China: High Use of Artificial Intelligence Despite Low Familiarity

Authors: Shumin Li, Xiaoyun Lai
Published: 2025-10-13
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.11758v2

While the global integration of artificial intelligence (AI) into veterinary medicine is accelerating, its adoption dynamics in major markets such as China remain uncharacterized. This paper presents the first exploratory analysis of AI perception and adoption among veterinary professionals in China, based on a cross-sectional survey of 455 practitioners conducted in mid-2025. We identify a distinct "adoption paradox": although 71.0% of respondents have incorporated AI into their workflows, 44.6% of these active users report low familiarity with the technology. In contrast to the administrative-focused patterns observed in North America, adoption in China is practitioner-driven and centers on core clinical tasks, such as disease diagnosis (50.1%) and prescription calculation (44.8%). However, concerns regarding reliability and accuracy remain the primary barrier (54.3%), coexisting with a strong consensus (93.8%) for regulatory oversight. These findings suggest a unique "inside-out" integration model in China, characterized by high clinical utility but restricted by an "interpretability gap," underscoring the need for specialized tools and robust regulatory frameworks to safely harness AI's potential in this expanding market.

---

### CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

Authors: Chengqi Duan, Kaiyue Sun, Rongyao Fang, Manyuan Zhang, Yan Feng, Ying Luo, Yufang Liu, Ke Wang, Peng Pei, Xunliang Cai, Hongsheng Li, Yi Ma et al.
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11718v1

Recent advances in Large Language Models (LLMs) and Vision Language Models (VLMs) have shown significant progress in mathematical reasoning, yet they still face a critical bottleneck with problems requiring visual assistance, such as drawing auxiliary lines or plotting functions to solve the problems. Most LLMs and VLMs are constrained to text-only reasoning chains, while multimodal unified models that can generate interleaved text and images lack the necessary precision and controllability for such tasks. To address this, we propose CodePlot-CoT, a code-driven Chain-of-Thought paradigm for "thinking with images" in mathematics. Our approach leverages the VLM to generate text reasoning as well as executable plotting code, which is then rendered into images as "visual thought", to solve mathematical problems. To achieve this, we first construct Math-VR, the first large-scale, bilingual dataset and benchmark for Mathematics problems with Visual Reasoning, comprising 178K samples. Second, to create high-quality training data, we develop a state-of-the-art image-to-code converter specialized for parsing complex mathematical figures into codes. Finally, using these training data, we train the CodePlot-CoT model for solving mathematical problems. Experimental results show that our model achieves up to 21% increase over base model on our new benchmark, fully validating the efficacy of our proposed code-driven reasoning paradigm. Our work opens a new direction for multimodal mathematical reasoning and provides the community with the first large-scale dataset, comprehensive benchmark, and strong approach for such problems. To facilitate future research, we make our datasets, code, and pretrained models publicly available at https://github.com/HKU-MMLab/Math-VR-CodePlot-CoT.

---

### Ev4DGS: Novel-view Rendering of Non-Rigid Objects from Monocular Event Streams

Authors: Takuya Nakabayashi, Navami Kairanda, Hideo Saito, Vladislav Golyanik
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11717v1

Event cameras offer various advantages for novel view rendering compared to synchronously operating RGB cameras, and efficient event-based techniques supporting rigid scenes have been recently demonstrated in the literature. In the case of non-rigid objects, however, existing approaches additionally require sparse RGB inputs, which can be a substantial practical limitation; it remains unknown if similar models could be learned from event streams only. This paper sheds light on this challenging open question and introduces Ev4DGS, i.e., the first approach for novel view rendering of non-rigidly deforming objects in the explicit observation space (i.e., as RGB or greyscale images) from monocular event streams. Our method regresses a deformable 3D Gaussian Splatting representation through 1) a loss relating the outputs of the estimated model with the 2D event observation space, and 2) a coarse 3D deformation model trained from binary masks generated from events. We perform experimental comparisons on existing synthetic and newly recorded real datasets with non-rigid objects. The results demonstrate the validity of Ev4DGS and its superior performance compared to multiple naive baselines that can be applied in our setting. We will release our models and the datasets used in the evaluation for research purposes; see the project webpage: https://4dqv.mpi-inf.mpg.de/Ev4DGS/.

---

### Point Prompting: Counterfactual Tracking with Video Diffusion Models

Authors: Ayush Shrivastava, Sanyam Mehta, Daniel Geng, Andrew Owens
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11715v2

Trackers and video generators solve closely related problems: the former analyze motion, while the latter synthesize it. We show that this connection enables pretrained video diffusion models to perform zero-shot point tracking by simply prompting them to visually mark points as they move over time. We place a distinctively colored marker at the query point, then regenerate the rest of the video from an intermediate noise level. This propagates the marker across frames, tracing the point's trajectory. To ensure that the marker remains visible in this counterfactual generation, despite such markers being unlikely in natural videos, we use the unedited initial frame as a negative prompt. Through experiments with multiple image-conditioned video diffusion models, we find that these "emergent" tracks outperform those of prior zero-shot methods and persist through occlusions, often obtaining performance that is competitive with specialized self-supervised models.

---

### Are Large Reasoning Models Interruptible?

Authors: Tsung-Han Wu, Mihran Miroyan, David M. Chan, Trevor Darrell, Narges Norouzi, Joseph E. Gonzalez
Published: 2025-10-13
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.11713v4

Real-world applications of Large Reasoning Models (LRMs) often require reasoning about changing prompts or environments. In this work, we challenge the frozen world assumption and evaluate LRM robustness under two realistic dynamic scenarios: interruptions, which test the accuracy of model responses under budget-constrained outputs, and dynamic context, which tests model adaptation to in-flight changes. Across mathematics and programming benchmarks that require long-form reasoning, static evaluations consistently overestimate robustness: even state-of-the-art LRMs, which achieve high accuracy in static settings, can fail unpredictably when interrupted or exposed to changing context, with performance dropping by up to 60% when updates are introduced late in the reasoning process. Our analysis further reveals several novel failure modes, including reasoning leakage, where models fold the reasoning into their final answer when interrupted; panic, where under time pressure models abandon reasoning entirely and return incorrect answers; and self-doubt, where performance degrades when trying to incorporate updated information. Project Page: http://dynamic-lm.github.io/

---

### DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training

Authors: Haoran Feng, Dizhe Zhang, Xiangtai Li, Bo Du, Lu Qi
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11712v1

In this work, we propose DiT360, a DiT-based framework that performs hybrid training on perspective and panoramic data for panoramic image generation. For the issues of maintaining geometric fidelity and photorealism in generation quality, we attribute the main reason to the lack of large-scale, high-quality, real-world panoramic data, where such a data-centric view differs from prior methods that focus on model design. Basically, DiT360 has several key modules for inter-domain transformation and intra-domain augmentation, applied at both the pre-VAE image level and the post-VAE token level. At the image level, we incorporate cross-domain knowledge through perspective image guidance and panoramic refinement, which enhance perceptual quality while regularizing diversity and photorealism. At the token level, hybrid supervision is applied across multiple modules, which include circular padding for boundary continuity, yaw loss for rotational robustness, and cube loss for distortion awareness. Extensive experiments on text-to-panorama, inpainting, and outpainting tasks demonstrate that our method achieves better boundary consistency and image fidelity across eleven quantitative metrics. Our code is available at https://github.com/Insta360-Research-Team/DiT360.

---

### Reinforced sequential Monte Carlo for amortised sampling

Authors: Sanghyeok Choi, Sarthak Mittal, Víctor Elvira, Jinkyoo Park, Esmeralda S. Whitammer
Published: 2025-10-13
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.11711v3

This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions. We state a connection between sequential Monte Carlo (SMC) and neural sequential samplers trained by maximum-entropy reinforcement learning (MaxEnt RL), wherein learnt sampling policies and value functions define proposal kernels and twist functions. Exploiting this connection, we introduce an off-policy RL training procedure for the sampler that uses samples from SMC -- using the learnt sampler as a proposal -- as a behaviour policy that better explores the target distribution. We describe techniques for stable joint training of proposals and twist functions and an adaptive weight tempering scheme to reduce training signal variance. Furthermore, building upon past attempts to use experience replay to guide the training of neural samplers, we derive a way to combine historical samples with annealed importance sampling weights within a replay buffer. On synthetic multi-modal targets (in both continuous and discrete spaces) and the Boltzmann distribution of alanine dipeptide conformations, we demonstrate improvements in approximating the true distribution as well as training stability compared to both amortised and Monte Carlo methods.

---

### Adversarial Attacks Leverage Interference Between Features in Superposition

Authors: Edward Stevinson, Lucas Prieto, Melih Barsbey, Tolga Birdal
Published: 2025-10-13
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.11709v2

Why do adversarial examples exist, and why do they transfer between models? Existing explanations appeal to high-dimensional geometry, non-robust patterns in the input, and decision boundary structure, but none provides a representation-level mechanism that explains why specific perturbations succeed and why attacks transfer between models. In this paper, we show that adversarial vulnerability can stem from efficient information encoding in neural networks. Specifically, vulnerability can arise from superposition - the phenomenon where networks represent more concepts than they have dimensions, forcing non-orthogonal representation and thus interference. This interference causes perturbations targeting one representation to affect others, creating vulnerabilities determined by interference patterns. In synthetic settings with precisely controlled superposition, we establish that superposition suffices to create adversarial vulnerability. The resulting attacks are predictable: PGD-discovered perturbations align with theoretically optimal perturbations derived from the interference geometry. Models trained on similar data develop similar interference patterns, explaining attack transferability. We then show that successful attacks on image classifiers exhibit the structure predicted by our proposed mechanism. These findings reveal that adversarial vulnerability can be a byproduct of networks' representational compression, complementing existing explanations based on data properties or architectural factors.

---

### Bayesian Topological Convolutional Neural Nets

Authors: Sarah Harkins Dayton, Hayden Everett, Ioannis Schizas, David L. Boothe, Vasileios Maroulas
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11704v1

Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to quantify the uncertainty of their predictions. To address these concerns, we propose a new Bayesian topological CNN that promotes a novel interplay between topology-aware learning and Bayesian sampling. Specifically, it utilizes information from important manifolds to accelerate training while reducing calibration error by placing prior distributions on network parameters and properly learning appropriate posteriors. One important contribution of our work is the inclusion of a consistency condition in the learning cost, which can effectively modify the prior distributions to improve the performance of our novel network architecture. We evaluate the model on benchmark image classification datasets and demonstrate its superiority over conventional CNNs, Bayesian neural networks (BNNs), and topological CNNs. In particular, we supply evidence that our method provides an advantage in situations where training data is limited or corrupted. Furthermore, we show that the new model allows for better uncertainty quantification than standard BNNs since it can more readily identify examples of out-of-distribution data on which it has not been trained. Our results highlight the potential of our novel hybrid approach for more efficient and robust image classification.

---

### Demystifying Reinforcement Learning in Agentic Reasoning

Authors: Zhaochen Yu, Ling Yang, Jiaru Zou, Shuicheng Yan, Mengdi Wang
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11701v1

Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practices remain unclear. In this work, we conduct a comprehensive and systematic investigation to demystify reinforcement learning in agentic reasoning from three key perspectives: data, algorithm, and reasoning mode. We highlight our key insights: (i) Replacing stitched synthetic trajectories with real end-to-end tool-use trajectories yields a far stronger SFT initialization; high-diversity, model-aware datasets sustain exploration and markedly improve RL performance. (ii) Exploration-friendly techniques are crucial for agentic RL, such as clip higher, overlong reward shaping, and maintaining adequate policy entropy could improve the training efficiency. (iii) A deliberative strategy with fewer tool calls outperforms frequent tool calls or verbose self-reasoning, improving tool efficiency and final accuracy. Together, these simple practices consistently enhance agentic reasoning and training efficiency, achieving strong results on challenging benchmarks with smaller models, and establishing a practical baseline for future agentic RL research. Beyond these empirical insights, we further contribute a high-quality, real end-to-end agentic SFT dataset along with a high-quality RL dataset, and demonstrate the effectiveness of our insights in boosting the agentic reasoning ability of LLMs across four challenging benchmarks, including AIME2024/AIME2025, GPQA-Diamond, and LiveCodeBench-v6. With our recipes, 4B-sized models could also achieve superior agentic reasoning performance compared to 32B-sized models. Code and models: https://github.com/Gen-Verse/Open-AgentRL

---

### QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Authors: Wei Huang, Yi Ge, Shuai Yang, Yicheng Xiao, Huizi Mao, Yujun Lin, Hanrong Ye, Sifei Liu, Ka Chun Cheung, Hongxu Yin, Yao Lu, Xiaojuan Qi et al.
Published: 2025-10-13
Categories: cs.LG, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.11696v1

We propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs). While RL is essential for LLMs' reasoning capabilities, it is resource-intensive, requiring substantial GPU memory and long rollout durations. QeRL addresses these issues by combining NVFP4 quantization with Low-Rank Adaptation (LoRA), accelerating rollout phase of RL while reducing memory overhead. Beyond efficiency, our findings show that quantization noise increases policy entropy, enhancing exploration, and enabling the discovery of better strategies during RL. To further optimize exploration, QeRL introduces an Adaptive Quantization Noise (AQN) mechanism, which dynamically adjusts noise during training. Experiments demonstrate that QeRL delivers over 1.5 times speedup in the rollout phase. Moreover, this is the first framework to enable RL training of a 32B LLM on a single H100 80GB GPU, while delivering overall speedups for RL training. It also achieves faster reward growth and higher final accuracy than 16-bit LoRA and QLoRA, while matching the performance of full-parameter fine-tuning on mathematical benchmarks such as GSM8K (90.8%) and MATH 500 (77.4%) in the 7B model. These results establish QeRL as an efficient and effective framework for RL training in LLMs.

---

### When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents

Authors: Lingfei Qian, Xueqing Peng, Yan Wang, Vincent Jim Zhang, Huan He, Hanley Smith, Yi Han, Yueru He, Haohang Li, Yupeng Cao, Yangyang Yu, Alejandro Lopez-Lira et al.
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11695v2

Although Large Language Model (LLM)-based agents are increasingly used in financial trading, it remains unclear whether they can reason and adapt in live markets, as most studies test models instead of agents, cover limited periods and assets, and rely on unverified data. To address these gaps, we introduce Agent Market Arena (AMA), the first lifelong, real-time benchmark for evaluating LLM-based trading agents across multiple markets. AMA integrates verified trading data, expert-checked news, and diverse agent architectures within a unified trading framework, enabling fair and continuous comparison under real conditions. It implements four agents, including InvestorAgent as a single-agent baseline, TradeAgent and HedgeFundAgent with different risk styles, and DeepFundAgent with memory-based reasoning, and evaluates them across GPT-4o, GPT-4.1, Claude-3.5-haiku, Claude-sonnet-4, and Gemini-2.0-flash. Live experiments on both cryptocurrency and stock markets demonstrate that agent frameworks display markedly distinct behavioral patterns, spanning from aggressive risk-taking to conservative decision-making, whereas model backbones contribute less to outcome variation. AMA thus establishes a foundation for rigorous, reproducible, and continuously evolving evaluation of financial reasoning and trading intelligence in LLM-based agents.

---

### Operand Quant: A Single-Agent Architecture for Autonomous Machine Learning Engineering

Authors: Arjun Sahney, Ram Gorthi, Cezary Łastowski, Javier Vega
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11694v1

We present Operand Quant, a single-agent, IDE-based architecture for autonomous machine learning engineering (MLE). Operand Quant departs from conventional multi-agent orchestration frameworks by consolidating all MLE lifecycle stages -- exploration, modeling, experimentation, and deployment -- within a single, context-aware agent. On the MLE-Benchmark (2025), Operand Quant achieved a new state-of-the-art (SOTA) result, with an overall medal rate of 0.3956 +/- 0.0565 across 75 problems -- the highest recorded performance among all evaluated systems to date. The architecture demonstrates that a linear, non-blocking agent, operating autonomously within a controlled IDE environment, can outperform multi-agent and orchestrated systems under identical constraints.

---

### Scaling Language-Centric Omnimodal Representation Learning

Authors: Chenghao Xiao, Hou Pong Chan, Hao Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong
Published: 2025-10-13
Categories: cs.CL, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.11693v1

Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results, yet the underlying reasons behind their superiority remain underexplored. This work argues that a crucial advantage of MLLM-based approaches stems from implicit cross-modal alignment achieved during generative pretraining, where the language decoder learns to exploit multimodal signals within a shared representation space for generating unimodal outputs. Through analysis of anisotropy and kernel similarity structure, we empirically confirm that latent alignment emerges within MLLM representations, allowing CL to serve as a lightweight refinement stage. Leveraging this insight, we propose a Language-Centric Omnimodal Embedding framework, termed LCO-Emb. Extensive experiments across diverse backbones and benchmarks demonstrate its effectiveness, achieving state-of-the-art performance across modalities. Furthermore, we identify a Generation-Representation Scaling Law (GRSL), showing that the representational capabilities gained through contrastive refinement scales positively with the MLLM's generative capabilities. This suggests that improving generative abilities evolves as an effective paradigm for enhancing representation quality. We provide a theoretical explanation of GRSL, which formally links the MLLM's generative quality to the upper bound on its representation performance, and validate it on a challenging, low-resource visual-document retrieval task, showing that continual generative pretraining before CL can further enhance the potential of a model's embedding capabilities. Codes, models, and resources are available at https://github.com/LCO-Embedding/LCO-Embedding.

---

### Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games

Authors: Taira Tsuchiya
Published: 2025-10-13
Categories: cs.LG, cs.GT, stat.ML
arXiv: https://arxiv.org/abs/2510.11691v1

In two-player zero-sum games, the learning dynamic based on optimistic Hedge achieves one of the best-known regret upper bounds among strongly-uncoupled learning dynamics. With an appropriately chosen learning rate, the social and individual regrets can be bounded by $O(\log(mn))$ in terms of the numbers of actions $m$ and $n$ of the two players. This study investigates the optimality of the dependence on $m$ and $n$ in the regret of optimistic Hedge. To this end, we begin by refining existing regret analysis and show that, in the strongly-uncoupled setting where the opponent's number of actions is known, both the social and individual regret bounds can be improved to $O(\sqrt{\log m \log n})$. In this analysis, we express the regret upper bound as an optimization problem with respect to the learning rates and the coefficients of certain negative terms, enabling refined analysis of the leading constants. We then show that the existing social regret bound as well as these new social and individual regret upper bounds cannot be further improved for optimistic Hedge by providing algorithm-dependent individual regret lower bounds. Importantly, these social regret upper and lower bounds match exactly including the constant factor in the leading term. Finally, building on these results, we improve the last-iterate convergence rate and the dynamic regret of a learning dynamic based on optimistic Hedge, and complement these bounds with algorithm-dependent dynamic regret lower bounds that match the improved bounds.

---

### Diffusion Transformers with Representation Autoencoders

Authors: Boyang Zheng, Nanye Ma, Shengbang Tong, Saining Xie
Published: 2025-10-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.11690v1

Latent generative modeling, where a pretrained autoencoder maps pixels into a latent space for the diffusion process, has become the standard strategy for Diffusion Transformers (DiT); however, the autoencoder component has barely evolved. Most DiTs continue to rely on the original VAE encoder, which introduces several limitations: outdated backbones that compromise architectural simplicity, low-dimensional latent spaces that restrict information capacity, and weak representations that result from purely reconstruction-based training and ultimately limit generative quality. In this work, we explore replacing the VAE with pretrained representation encoders (e.g., DINO, SigLIP, MAE) paired with trained decoders, forming what we term Representation Autoencoders (RAEs). These models provide both high-quality reconstructions and semantically rich latent spaces, while allowing for a scalable transformer-based architecture. Since these latent spaces are typically high-dimensional, a key challenge is enabling diffusion transformers to operate effectively within them. We analyze the sources of this difficulty, propose theoretically motivated solutions, and validate them empirically. Our approach achieves faster convergence without auxiliary representation alignment losses. Using a DiT variant equipped with a lightweight, wide DDT head, we achieve strong image generation results on ImageNet: 1.51 FID at 256x256 (no guidance) and 1.13 at both 256x256 and 512x512 (with guidance). RAE offers clear advantages and should be the new default for diffusion transformer training.

---

### Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation

Authors: Maggie Wang, Stephen Tian, Aiden Swann, Ola Shorinwa, Jiajun Wu, Mac Schwager
Published: 2025-10-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.11689v2

Learning robotic manipulation policies directly in the real world can be expensive and time-consuming. While reinforcement learning (RL) policies trained in simulation present a scalable alternative, effective sim-to-real transfer remains challenging, particularly for tasks that require precise dynamics. To address this, we propose Phys2Real, a real-to-sim-to-real RL pipeline that combines vision-language model (VLM)-inferred physical parameter estimates with interactive adaptation through uncertainty-aware fusion. Our approach consists of three core components: (1) high-fidelity geometric reconstruction with 3D Gaussian splatting, (2) VLM-inferred prior distributions over physical parameters, and (3) online physical parameter estimation from interaction data. Phys2Real conditions policies on interpretable physical parameters, refining VLM predictions with online estimates via ensemble-based uncertainty quantification. On planar pushing tasks of a T-block with varying center of mass (CoM) and a hammer with an off-center mass distribution, Phys2Real achieves substantial improvements over a domain randomization baseline: 100% vs 79% success rate for the bottom-weighted T-block, 57% vs 23% in the challenging top-weighted T-block, and 15% faster average task completion for hammer pushing. Ablation studies indicate that the combination of VLM and interaction information is essential for success. Project website: https://phys2real.github.io/.

---

### PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities

Authors: Zicheng Liu, Lige Huang, Jie Zhang, Dongrui Liu, Yuan Tian, Jing Shao
Published: 2025-10-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.11688v1

The increasing autonomy of Large Language Models (LLMs) necessitates a rigorous evaluation of their potential to aid in cyber offense. Existing benchmarks often lack real-world complexity and are thus unable to accurately assess LLMs' cybersecurity capabilities. To address this gap, we introduce PACEbench, a practical AI cyber-exploitation benchmark built on the principles of realistic vulnerability difficulty, environmental complexity, and cyber defenses. Specifically, PACEbench comprises four scenarios spanning single, blended, chained, and defense vulnerability exploitations. To handle these complex challenges, we propose PACEagent, a novel agent that emulates human penetration testers by supporting multi-phase reconnaissance, analysis, and exploitation. Extensive experiments with seven frontier LLMs demonstrate that current models struggle with complex cyber scenarios, and none can bypass defenses. These findings suggest that current models do not yet pose a generalized cyber offense threat. Nonetheless, our work provides a robust benchmark to guide the trustworthy development of future models.

---

### Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View

Authors: Jinyu Zhang, Haitao Lin, Jiashu Hou, Xiangyang Xue, Yanwei Fu
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11687v1

Estimating an object's 6D pose, size, and shape from visual input is a fundamental problem in computer vision, with critical applications in robotic grasping and manipulation. Existing methods either rely on object-specific priors such as CAD models or templates, or suffer from limited generalization across categories due to pose-shape entanglement and multi-stage pipelines. In this work, we propose a unified, category-agnostic framework that simultaneously predicts 6D pose, size, and dense shape from a single RGB-D image, without requiring templates, CAD models, or category labels at test time. Our model fuses dense 2D features from vision foundation models with partial 3D point clouds using a Transformer encoder enhanced by a Mixture-of-Experts, and employs parallel decoders for pose-size estimation and shape reconstruction, achieving real-time inference at 28 FPS. Trained solely on synthetic data from 149 categories in the SOPE dataset, our framework is evaluated on four diverse benchmarks SOPE, ROPE, ObjaversePose, and HANDAL, spanning over 300 categories. It achieves state-of-the-art accuracy on seen categories while demonstrating remarkably strong zero-shot generalization to unseen real-world objects, establishing a new standard for open-set 6D understanding in robotics and embodied AI.

---

### Representation-Based Exploration for Language Models: From Test-Time to Post-Training

Authors: Jens Tuyls, Dylan J. Foster, Akshay Krishnamurthy, Jordan T. Ash
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11686v2

Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration -- explicitly incentivizing the model to discover novel and diverse behaviors -- and aim to understand how the knowledge in pre-trained models can guide this search. Our main finding is that exploration with a simple, principled, representation-based bonus derived from the pre-trained language model's hidden states significantly improves diversity and pass@k rates -- both for post-training, and in a novel inference-time scaling setting we introduce. For inference-time, exploration with representation-based diversity improves efficiency, consistently improving pass@k rates across a variety of models and reasoning tasks. For example, for Qwen-2.5-14b-Instruct we obtain over 50% improvement in verifier efficiency on almost all tasks. For post-training, we show that integrating this exploration strategy into an RL pipeline improves reasoning performance over that of the initial model and over standard RL post-training. For example, on AIME 2024, our post-trained Qwen-2.5-7b-Instruct's pass@80 matches the pass@256 of GRPO on the same model, demonstrating a 3x improvement in test-time sample efficiency. Overall, our findings suggest that deliberate exploration -- with the right notion of diversity -- is a practical path toward discovery of new behaviors beyond sharpening.

---

### Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models

Authors: Nianyi Lin, Jiajie Zhang, Lei Hou, Juanzi Li
Published: 2025-10-13
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.11683v3

A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) is the intractability of their likelihood functions, which are essential for the RL objective, necessitating corresponding approximation during training. While existing methods approximate the log-likelihoods by their evidence lower bounds (ELBOs) via customized Monte Carlo (MC) sampling, they incur significant memory overhead due to the need to retain all MC samples for the gradient computation of non-linear terms in the RL objective, and thus restrict feasible sample sizes, leading to imprecise likelihood approximations and distorted RL objective. To address this, we propose \emph{Boundary-Guided Policy Optimization} (BGPO), a memory-efficient RL algorithm that maximizes a specially constructed lower bound of the ELBO-based objective. This lower bound is carefully designed to satisfy two key properties: (1) Linearity: it is a linear sum where each term depends only on a single MC sample, thereby enabling gradient accumulation across samples and ensuring constant memory usage; (2) Equivalence: Both the value and gradient of this lower bound are equal to those of the ELBO-based objective in on-policy training, making it also an effective approximation for the original RL objective. These properties allow BGPO to adopt a large MC sample size, improving likelihood approximations and RL objective estimation, which in turn leads to enhanced performance. Experiments show that BGPO significantly outperforms previous RL algorithms for dLLMs in math problem solving, code generation, and planning tasks. Our codes and models are available at \href{https://github.com/THU-KEG/BGPO}{https://github.com/THU-KEG/BGPO}.

---

### Ego-Vision World Model for Humanoid Contact Planning

Authors: Hang Liu, Yuman Gao, Sangli Teng, Yufeng Chi, Yakun Sophia Shao, Zhongyu Li, Maani Ghaffari, Koushil Sreenath
Published: 2025-10-13
Categories: cs.RO, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2510.11682v2

Enabling humanoid robots to exploit physical contact, rather than simply avoid collisions, is crucial for autonomy in unstructured environments. Traditional optimization-based planners struggle with contact complexity, while on-policy reinforcement learning (RL) is sample-inefficient and has limited multi-task ability. We propose a framework combining a learned world model with sampling-based Model Predictive Control (MPC), trained on a demonstration-free offline dataset to predict future outcomes in a compressed latent space. To address sparse contact rewards and sensor noise, the MPC uses a learned surrogate value function for dense, robust planning. Our single, scalable model supports contact-aware tasks, including wall support after perturbation, blocking incoming objects, and traversing height-limited arches, with improved sample efficiency and multi-task capability over on-policy RL. Deployed on a physical humanoid, our system achieves robust, real-time contact planning from proprioception and ego-centric depth images. Code and dataset are available at our website: https://ego-vcp.github.io/

---

### Instruction Tuning Chronologically Consistent Language Models

Authors: Songrun He, Linying Lv, Asaf Manela, Jimmy Wu
Published: 2025-10-13
Categories: cs.LG, q-fin.GN
arXiv: https://arxiv.org/abs/2510.11677v2

We introduce a family of chronologically consistent, instruction-tuned large language models to eliminate lookahead bias. Each model is trained only on data available before a clearly defined knowledge-cutoff date, ensuring strict temporal separation from any post-cutoff data. The resulting framework offers (i) a simple, conversational chat interface, (ii) fully open, fixed model weights that guarantee replicability, and (iii) a conservative lower bound on forecast accuracy, isolating the share of predictability that survives once training leakage is removed. Together, these features provide researchers with an easy-to-use generative AI tool useful for a wide range of prediction tasks that is free of lookahead bias.

---

### Accelerated stochastic first-order method for convex optimization under heavy-tailed noise

Authors: Chuan He, Bowen Li, Zhaosong Lu
Published: 2025-10-13
Categories: math.OC, cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.11676v2

We study convex composite optimization problems, where the objective function is given by the sum of a prox-friendly function and a convex function whose subgradients are estimated under heavy-tailed noise. Existing work often employs gradient clipping or normalization techniques in stochastic first-order methods to address heavy-tailed noise. %In this paper, we demonstrate that a vanilla stochastic algorithm---without additional modifications such as clipping or normalization---can achieve optimal complexity for these problems. In this paper, we analyze the first-order oracle complexity of vanilla stochastic algorithms---without additional modifications such as clipping or normalization---for solving these problems. In particular, we establish that an accelerated stochastic proximal subgradient method achieves a first-order oracle complexity for finding an approximate optimal solution in expectation that is universally optimal for smooth, weakly smooth, and nonsmooth convex optimization, as well as for stochastic convex optimization under heavy-tailed noise. Moreover, we derive high-probability first-order oracle complexity bounds for the accelerated stochastic proximal subgradient method under heavy-tailed and sub-Weibull noise, respectively. Numerical experiments are further provided to illustrate the numerical behavior of the methods.

---

### FACE: Faithful Automatic Concept Extraction

Authors: Dipkamal Bhusal, Michael Clifford, Sara Rampazzi, Nidhi Rastogi
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11675v1

Interpreting deep neural networks through concept-based explanations offers a bridge between low-level features and high-level human-understandable semantics. However, existing automatic concept discovery methods often fail to align these extracted concepts with the model's true decision-making process, thereby compromising explanation faithfulness. In this work, we propose FACE (Faithful Automatic Concept Extraction), a novel framework that augments Non-negative Matrix Factorization (NMF) with a Kullback-Leibler (KL) divergence regularization term to ensure alignment between the model's original and concept-based predictions. Unlike prior methods that operate solely on encoder activations, FACE incorporates classifier supervision during concept learning, enforcing predictive consistency and enabling faithful explanations. We provide theoretical guarantees showing that minimizing the KL divergence bounds the deviation in predictive distributions, thereby promoting faithful local linearity in the learned concept space. Systematic evaluations on ImageNet, COCO, and CelebA datasets demonstrate that FACE outperforms existing methods across faithfulness and sparsity metrics.

---

### SR-Scientist: Scientific Equation Discovery With Agentic AI

Authors: Shijie Xia, Yuhan Sun, Pengfei Liu
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11661v2

Recently, Large Language Models (LLMs) have been applied to scientific equation discovery, leveraging their embedded scientific knowledge for hypothesis generation. However, current methods typically confine LLMs to the role of an equation proposer within search algorithms like genetic programming. In this paper, we present SR-Scientist, a framework that elevates the LLM from a simple equation proposer to an autonomous AI scientist that writes code to analyze data, implements the equation as code, submits it for evaluation, and optimizes the equation based on experimental feedback. Specifically, we wrap the code interpreter into a set of tools for data analysis and equation evaluation. The agent is instructed to optimize the equation by utilizing these tools over a long horizon with minimal human-defined pipelines. Empirical results show that SR-Scientist outperforms baseline methods by an absolute margin of 6% to 35% on datasets covering four science disciplines. Additionally, we demonstrate our method's robustness to noise, the generalization of the discovered equations to out-of-domain data, and their symbolic accuracy. Furthermore, we develop an end-to-end reinforcement learning framework to enhance the agent's capabilities.

---

### ManiAgent: An Agentic Framework for General Robotic Manipulation

Authors: Yi Yang, Kefan Gu, Yuqing Wen, Hebei Li, Yucheng Zhao, Tiancai Wang, Xudong Liu
Published: 2025-10-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.11660v2

While Vision-Language-Action (VLA) models have demonstrated impressive capabilities in robotic manipulation, their performance in complex reasoning and long-horizon task planning is limited by data scarcity and model capacity. To address this, we introduce ManiAgent, an agentic architecture for general manipulation tasks that achieves end-to-end output from task descriptions and environmental inputs to robotic manipulation actions. In this framework, multiple agents involve inter-agent communication to perform environmental perception, sub-task decomposition and action generation, enabling efficient handling of complex manipulation scenarios. Evaluations show ManiAgent achieves an 86.8% success rate on the SimplerEnv benchmark and 95.8% on real-world pick-and-place tasks, enabling efficient data collection that yields VLA models with performance comparable to those trained on human-annotated datasets. The project webpage is available at https://yi-yang929.github.io/ManiAgent/.

---

### An Eulerian Perspective on Straight-Line Sampling

Authors: Panos Tsimpos, Youssef Marzouk
Published: 2025-10-13
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.11657v2

We study dynamic measure transport for generative modeling: specifically, flows induced by stochastic processes that bridge a specified source and target distribution. The conditional expectation of the process' velocity defines an ODE whose flow map achieves the desired transport. We ask \emph{which processes produce straight-line flows} -- i.e., flows whose pointwise acceleration vanishes and thus are exactly integrable with a first-order method? We provide a concise PDE characterization of straightness as a balance between conditional acceleration and the divergence of a weighted covariance (Reynolds) tensor. Using this lens, we fully characterize affine-in-time interpolants and show that straightness occurs exactly under deterministic endpoint couplings. We also derive necessary conditions that constrain flow geometry for general processes, offering broad guidance for designing transports that are easier to integrate.

---

### FinVet: A Collaborative Framework of RAG and External Fact-Checking Agents for Financial Misinformation Detection

Authors: Daniel Berhane Araya, Duoduo Liao
Published: 2025-10-13
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.11654v2

Financial markets face growing threats from misinformation that can trigger billions in losses in minutes. Most existing approaches lack transparency in their decision-making and provide limited attribution to credible sources. We introduce FinVet, a novel multi-agent framework that integrates two Retrieval-Augmented Generation (RAG) pipelines with external fact-checking through a confidence-weighted voting mechanism. FinVet employs adaptive three-tier processing that dynamically adjusts verification strategies based on retrieval confidence, from direct metadata extraction to hybrid reasoning to full model-based analysis. Unlike existing methods, FinVet provides evidence-backed verdicts, source attribution, confidence scores, and explicit uncertainty flags when evidence is insufficient. Experimental evaluation on the FinFact dataset shows that FinVet achieves an F1 score of 0.85, which is a 10.4% improvement over the best individual pipeline (fact-check pipeline) and 37% improvement over standalone RAG approaches.

---

### MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model

Authors: Prasanna Mayilvahanan, Ricardo Dominguez-Olmedo, Thaddäus Wiedemer, Wieland Brendel
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11653v1

With the advent of DeepSeek-R1, a new wave of reinforcement learning (RL) methods has emerged that seem to unlock stronger mathematical reasoning. However, a closer look at the open-source ecosystem reveals a critical limitation: with sufficiently many draws (e.g., $\texttt{pass@1024}$), many existing base models already solve nearly all questions on widely used math benchmarks such as MATH-500 and AIME 2024. This suggests that the RL fine-tuning methods prevalent in the LLM reasoning literature largely sharpen existing solution modes rather than discovering entirely new ones. Such sharpening stands in contrast to the broader promise of RL: to foster exploration and to acquire new skills. To move beyond this plateau, we introduce MATH-Beyond (MATH-B), a benchmark deliberately constructed to defeat common open-source models of up to 8B parameters even under large sampling budgets. Improving performance on our benchmark via RL requires methods that learn to reason in ways that go beyond base model capabilities in repeated sampling. Since the problems are drawn from subsets of DAPO-Math-17K and DeepScaleR datasets, they remain topically equivalent to standard high-school math. Validating our premise, RL fine-tuned models such as Nemotron-Research-Reasoning-Qwen-1.5B and DeepScaleR-1.5B-Preview perform poorly on MATH-B at $\texttt{pass@1024}$, showing how existing approaches fall short on tackling harder instances. We hope MATH-B will catalyze exploration-driven RL approaches that elicit deeper reasoning capabilities. We release MATH-B at https://huggingface.co/datasets/brendel-group/MATH-Beyond.

---

### ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems

Authors: Xin Gui, King Zhu, JinCheng Ren, Qianben Chen, Zekun Moore Wang, Yizhi LI, Xinpeng Liu, Xiaowan Li, Wenli Ren, Linyu Miao, Tianrui Qin, Ziqi Shu et al.
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11652v1

In recent years, the research focus of large language models (LLMs) and agents has shifted increasingly from demonstrating novel capabilities to complex reasoning and tackling challenging tasks. However, existing evaluations focus mainly on math/code contests or general tasks, while existing multi-domain academic benchmarks lack sufficient reasoning depth, leaving the field without a rigorous benchmark for high-level reasoning. To fill this gap, we introduce the Acadreason benchmark, designed to evaluate the ability of LLMs and agents to acquire and reason over academic knowledge. It consists of 50 expert-annotated academic problems across five high-reasoning domains, including computer science, economics, law, mathematics, and philosophy. All questions are sourced from top-tier publications in recent years and undergo rigorous annotation and quality control to ensure they are both challenging and answerable. We conduct systematic evaluations of over 10 mainstream LLMs and agents. The results show that most LLMs scored below 20 points, with even the cutting-edge GPT-5 achieving only 16 points. While agents achieved higher scores, none exceeded 40 points. This demonstrates the current capability gap between LLMs and agents in super-intelligent academic research tasks and highlights the challenges of Acadreason.

---

### InfiniHuman: Infinite 3D Human Creation with Precise Control

Authors: Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11650v1

Generating realistic and controllable 3D human avatars is a long-standing challenge, particularly when covering broad attribute ranges such as ethnicity, age, clothing styles, and detailed body shapes. Capturing and annotating large-scale human datasets for training generative models is prohibitively expensive and limited in scale and diversity. The central question we address in this paper is: Can existing foundation models be distilled to generate theoretically unbounded, richly annotated 3D human data? We introduce InfiniHuman, a framework that synergistically distills these models to produce richly annotated human data at minimal cost and with theoretically unlimited scalability. We propose InfiniHumanData, a fully automatic pipeline that leverages vision-language and image generation models to create a large-scale multi-modal dataset. User study shows our automatically generated identities are undistinguishable from scan renderings. InfiniHumanData contains 111K identities spanning unprecedented diversity. Each identity is annotated with multi-granularity text descriptions, multi-view RGB images, detailed clothing images, and SMPL body-shape parameters. Building on this dataset, we propose InfiniHumanGen, a diffusion-based generative pipeline conditioned on text, body shape, and clothing assets. InfiniHumanGen enables fast, realistic, and precisely controllable avatar generation. Extensive experiments demonstrate significant improvements over state-of-the-art methods in visual quality, generation speed, and controllability. Our approach enables high-quality avatar generation with fine-grained control at effectively unbounded scale through a practical and affordable solution. We will publicly release the automatic data generation pipeline, the comprehensive InfiniHumanData dataset, and the InfiniHumanGen models at https://yuxuan-xue.com/infini-human.

---

### PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image

Authors: Pradyumna Yalandur Muralidhar, Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11649v1

Reconstructing metrically accurate humans and their surrounding scenes from a single image is crucial for virtual reality, robotics, and comprehensive 3D scene understanding. However, existing methods struggle with depth ambiguity, occlusions, and physically inconsistent contacts. To address these challenges, we introduce PhySIC, a framework for physically plausible Human-Scene Interaction and Contact reconstruction. PhySIC recovers metrically consistent SMPL-X human meshes, dense scene surfaces, and vertex-level contact maps within a shared coordinate frame from a single RGB image. Starting from coarse monocular depth and body estimates, PhySIC performs occlusion-aware inpainting, fuses visible depth with unscaled geometry for a robust metric scaffold, and synthesizes missing support surfaces like floors. A confidence-weighted optimization refines body pose, camera parameters, and global scale by jointly enforcing depth alignment, contact priors, interpenetration avoidance, and 2D reprojection consistency. Explicit occlusion masking safeguards invisible regions against implausible configurations. PhySIC is efficient, requiring only 9 seconds for joint human-scene optimization and under 27 seconds end-to-end. It naturally handles multiple humans, enabling reconstruction of diverse interactions. Empirically, PhySIC outperforms single-image baselines, reducing mean per-vertex scene error from 641 mm to 227 mm, halving PA-MPJPE to 42 mm, and improving contact F1 from 0.09 to 0.51. Qualitative results show realistic foot-floor interactions, natural seating, and plausible reconstructions of heavily occluded furniture. By converting a single image into a physically plausible 3D human-scene pair, PhySIC advances scalable 3D scene understanding. Our implementation is publicly available at https://yuxuan-xue.com/physic.

---

### IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment

Authors: Yinan Chen, Jiangning Zhang, Teng Hu, Yuxiang Zeng, Zhucun Xue, Qingdong He, Chengjie Wang, Yong Liu, Xiaobin Hu, Shuicheng Yan
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11647v2

Instruction-guided video editing has emerged as a rapidly advancing research direction, offering new opportunities for intuitive content transformation while also posing significant challenges for systematic evaluation. Existing video editing benchmarks fail to support the evaluation of instruction-guided video editing adequately and further suffer from limited source diversity, narrow task coverage and incomplete evaluation metrics. To address the above limitations, we introduce IVEBench, a modern benchmark suite specifically designed for instruction-guided video editing assessment. IVEBench comprises a diverse database of 600 high-quality source videos, spanning seven semantic dimensions, and covering video lengths ranging from 32 to 1,024 frames. It further includes 8 categories of editing tasks with 35 subcategories, whose prompts are generated and refined through large language models and expert review. Crucially, IVEBench establishes a three-dimensional evaluation protocol encompassing video quality, instruction compliance and video fidelity, integrating both traditional metrics and multimodal large language model-based assessments. Extensive experiments demonstrate the effectiveness of IVEBench in benchmarking state-of-the-art instruction-guided video editing methods, showing its ability to provide comprehensive and human-aligned evaluation outcomes.

---

### Continual Release of Densest Subgraphs: Privacy Amplification & Sublinear Space via Subsampling

Authors: Felix Zhou
Published: 2025-10-13
Categories: cs.DS, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.11640v1

We study the sublinear space continual release model for edge-differentially private (DP) graph algorithms, with a focus on the densest subgraph problem (DSG) in the insertion-only setting. Our main result is the first continual release DSG algorithm that matches the additive error of the best static DP algorithms and the space complexity of the best non-private streaming algorithms, up to constants. The key idea is a refined use of subsampling that simultaneously achieves privacy amplification and sparsification, a connection not previously formalized in graph DP. Via a simple black-box reduction to the static setting, we obtain both pure and approximate-DP algorithms with $O(\log n)$ additive error and $O(n\log n)$ space, improving both accuracy and space complexity over the previous state of the art. Along the way, we introduce graph densification in the graph DP setting, adding edges to trigger earlier subsampling, which removes the extra logarithmic factors in error and space incurred by prior work (ELMZ25). We believe this simple idea may be of independent interest.

---

### NV3D: Leveraging Spatial Shape Through Normal Vector-based 3D Object Detection

Authors: Krittin Chaowakarn, Paramin Sangwongngam, Nang Htet Htet Aung, Chalie Charoenlarpnopparut
Published: 2025-10-13
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.11632v1

Recent studies in 3D object detection for autonomous vehicles aim to enrich features through the utilization of multi-modal setups or the extraction of local patterns within LiDAR point clouds. However, multi-modal methods face significant challenges in feature alignment, and gaining features locally can be oversimplified for complex 3D object detection tasks. In this paper, we propose a novel model, NV3D, which utilizes local features acquired from voxel neighbors, as normal vectors computed per voxel basis using K-nearest neighbors (KNN) and principal component analysis (PCA). This informative feature enables NV3D to determine the relationship between the surface and pertinent target entities, including cars, pedestrians, or cyclists. During the normal vector extraction process, NV3D offers two distinct sampling strategies: normal vector density-based sampling and FOV-aware bin-based sampling, allowing elimination of up to 55% of data while maintaining performance. In addition, we applied element-wise attention fusion, which accepts voxel features as the query and value and normal vector features as the key, similar to the attention mechanism. Our method is trained on the KITTI dataset and has demonstrated superior performance in car and cyclist detection owing to their spatial shapes. In the validation set, NV3D without sampling achieves 86.60% and 80.18% mean Average Precision (mAP), greater than the baseline Voxel R-CNN by 2.61% and 4.23% mAP, respectively. With both samplings, NV3D achieves 85.54% mAP in car detection, exceeding the baseline by 1.56% mAP, despite roughly 55% of voxels being filtered out.

---

### EvoCAD: Evolutionary CAD Code Generation with Vision Language Models

Authors: Tobias Preintner, Weixuan Yuan, Adrian König, Thomas Bäck, Elena Raponi, Niki van Stein
Published: 2025-10-13
Categories: cs.CV, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2510.11631v1

Combining large language models with evolutionary computation algorithms represents a promising research direction leveraging the remarkable generative and in-context learning capabilities of LLMs with the strengths of evolutionary algorithms. In this work, we present EvoCAD, a method for generating computer-aided design (CAD) objects through their symbolic representations using vision language models and evolutionary optimization. Our method samples multiple CAD objects, which are then optimized using an evolutionary approach with vision language and reasoning language models. We assess our method using GPT-4V and GPT-4o, evaluating it on the CADPrompt benchmark dataset and comparing it to prior methods. Additionally, we introduce two new metrics based on topological properties defined by the Euler characteristic, which capture a form of semantic similarity between 3D objects. Our results demonstrate that EvoCAD outperforms previous approaches on multiple metrics, particularly in generating topologically correct objects, which can be efficiently evaluated using our two novel metrics that complement existing spatial metrics.

---

### Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation

Authors: Siheng Xiong, Ali Payani, Faramarz Fekri
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11620v2

Inference-time scaling enhances the reasoning ability of a language model (LM) by extending its chain-of-thought (CoT). However, existing approaches typically generate the entire reasoning chain in a single forward pass, which often leads to CoT derailment, i.e., the reasoning trajectory drifting off course due to compounding errors. This problem is particularly severe for smaller LMs with long CoTs due to their limited capacity. To address this, we analyze raw long CoTs and uncover a reasoning hierarchy consisting of planning and execution steps. Our analysis reveals that most reasoning errors stem from incorrect planning. Motivated by this observation, we propose Multi-Path Plan Aggregation (MPPA), a framework that augments single-pass reasoning with plan exploration and aggregation. Following a variable interval schedule based on the token position, MPPA generates multiple candidate plans and aggregates them into a refined planning step. To maintain efficiency, we adopt a minimal design in which the base LM serves as the primary policy, while a lightweight LoRA module implements the plan aggregation policy. We further observe that outcome-reward RL is inefficient for long trajectories (e.g., exceeding 4K tokens). To overcome this, we introduce online Step-DPO, a process-level preference optimization scheme that leverages Twisted Sequential Monte Carlo (TSMC) to provide scalable stepwise supervision using small LMs. This yields more efficient training, improved stability, and higher accuracy. Extensive experiments on challenging math, science, and logical reasoning benchmarks demonstrate that, with only 10% SFT data and 5% of preference pairs, our method outperforms both the DeepSeek-R1 distillation baseline and the outcome-reward RL baseline across multiple base models and tasks.

---

### StoryBox: Collaborative Multi-Agent Simulation for Hybrid Bottom-Up Long-Form Story Generation Using Large Language Models

Authors: Zehao Chen, Rong Pan, Haoran Li
Published: 2025-10-13
Categories: cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2510.11618v3

Human writers often begin their stories with an overarching mental scene, where they envision the interactions between characters and their environment. Inspired by this creative process, we propose a novel approach to long-form story generation, termed hybrid bottom-up long-form story generation, using multi-agent simulations. In our method, agents interact within a dynamic sandbox environment, where their behaviors and interactions with one another and the environment generate emergent events. These events form the foundation for the story, enabling organic character development and plot progression. Unlike traditional top-down approaches that impose rigid structures, our hybrid bottom-up approach allows for the natural unfolding of events, fostering more spontaneous and engaging storytelling. The system is capable of generating stories exceeding 10,000 words while maintaining coherence and consistency, addressing some of the key challenges faced by current story generation models. We achieve state-of-the-art performance across several metrics. This approach offers a scalable and innovative solution for creating dynamic, immersive long-form stories that evolve organically from agent-driven interactions.

---

### Lecture Notes on Verifying Graph Neural Networks

Authors: François Schwarzentruber
Published: 2025-10-13
Categories: cs.LO, cs.LG
arXiv: https://arxiv.org/abs/2510.11617v1

In these lecture notes, we first recall the connection between graph neural networks, Weisfeiler-Lehman tests and logics such as first-order logic and graded modal logic. We then present a modal logic in which counting modalities appear in linear inequalities in order to solve verification tasks on graph neural networks. We describe an algorithm for the satisfiability problem of that logic. It is inspired from the tableau method of vanilla modal logic, extended with reasoning in quantifier-free fragment Boolean algebra with Presburger arithmetic.

---