# Research Papers — 2025-10 · bundle page 32 of 217

> Full-text markdown of papers #1551–1600 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/32
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/31.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/33.md)

### AI and the Decentering of Disciplinary Creativity

Authors: Eamon Duede
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23734v1

This paper examines the role of artificial intelligence in scientific problem-solving, with a focus on its implications for disciplinary creativity. Drawing on recent work in the philosophy of creativity, I distinguish between creative approaches and creative products, and introduce the concept of disciplinary creativity -the creative application of discipline-specific expertise to a valued problem within that field. Through two cases in mathematics, I show that while computation can extend disciplinary creativity, certain approaches involving AI can serve to displace it. This displacement has the potential to alter (and, perhaps, diminish) the value of scientific pursuit.

---

### Evaluating Long-Term Memory for Long-Context Question Answering

Authors: Alessandra Terranova, Björn Ross, Alexandra Birch
Published: 2025-10-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.23730v2

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types of memory are most effective for long-context conversational tasks. We present a systematic evaluation of memory-augmented methods on long-context dialogues annotated for question-answering tasks that require diverse reasoning strategies. We analyse full-context prompting, semantic memory through retrieval-augmented generation and agentic memory, episodic memory through in-context learning, and procedural memory through prompt optimization. Our findings show that memory-augmented approaches reduce token usage by over 90\% while maintaining competitive accuracy. Memory architecture complexity should scale with model capability, with foundation models benefitting most from RAG, and stronger instruction-tuned models gaining from episodic learning through reflections and more complex agentic semantic memory. In particular, episodic memory can help LLMs recognise the limits of their own knowledge.

---

### MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection

Authors: Anisha Saha, Varsha Suresh, Timothy Hospedales, Vera Demberg
Published: 2025-10-27
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.23727v1

Sarcasm is a specific type of irony which involves discerning what is said from what is meant. Detecting sarcasm depends not only on the literal content of an utterance but also on non-verbal cues such as speaker's tonality, facial expressions and conversational context. However, current multimodal models struggle with complex tasks like sarcasm detection, which require identifying relevant cues across modalities and pragmatically reasoning over them to infer the speaker's intention. To explore these limitations in VideoLMs, we introduce MUStReason, a diagnostic benchmark enriched with annotations of modality-specific relevant cues and underlying reasoning steps to identify sarcastic intent. In addition to benchmarking sarcasm classification performance in VideoLMs, using MUStReason we quantitatively and qualitatively evaluate the generated reasoning by disentangling the problem into perception and reasoning, we propose PragCoT, a framework that steers VideoLMs to focus on implied intentions over literal meaning, a property core to detecting sarcasm.

---

### In Search of the Unknown Unknowns: A Multi-Metric Distance Ensemble for Out of Distribution Anomaly Detection in Astronomical Surveys

Authors: Siddharth Chaini, Federica B. Bianco, Ashish Mahabal
Published: 2025-10-27
Categories: astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2510.23702v1

Distance-based methods involve the computation of distance values between features and are a well-established paradigm in machine learning. In anomaly detection, anomalies are identified by their large distance from normal data points. However, the performance of these methods often hinges on a single, user-selected distance metric (e.g., Euclidean), which may not be optimal for the complex, high-dimensional feature spaces common in astronomy. Here, we introduce a novel anomaly detection method, Distance Multi-Metric Anomaly Detection (DiMMAD), which uses an ensemble of distance metrics to find novelties. Using multiple distance metrics is effectively equivalent to using different geometries in the feature space. By using a robust ensemble of diverse distance metrics, we overcome the metric-selection problem, creating an anomaly score that is not reliant on any single definition of distance. We demonstrate this multi-metric approach as a tool for simple, interpretable scientific discovery on astronomical time series -- (1) with simulated data for the upcoming Vera C. Rubin Observatory Legacy Survey of Space and Time, and (2) real data from the Zwicky Transient Facility. We find that DiMMAD excels at out-of-distribution anomaly detection -- anomalies in the data that might be new classes -- and beats other state-of-the-art methods in the goal of maximizing the diversity of new classes discovered. For rare in-distribution anomaly detection, DiMMAD performs similarly to other methods, but may allow for improved interpretability. All our code is open source: DiMMAD is implemented within DistClassiPy: https://github.com/sidchaini/distclassipy/, while all code to reproduce the results of this paper is available here: https://github.com/sidchaini/dimmad/.

---

### On the Societal Impact of Machine Learning

Authors: Joachim Baumann
Published: 2025-10-27
Categories: cs.LG, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.23693v2

This PhD thesis investigates the societal impact of machine learning (ML). ML increasingly informs consequential decisions and recommendations, significantly affecting many aspects of our lives. As these data-driven systems are often developed without explicit fairness considerations, they carry the risk of discriminatory effects. The contributions in this thesis enable more appropriate measurement of fairness in ML systems, systematic decomposition of ML systems to anticipate bias dynamics, and effective interventions that reduce algorithmic discrimination while maintaining system utility. I conclude by discussing ongoing challenges and future research directions as ML systems, including generative artificial intelligence, become increasingly integrated into society. This work offers a foundation for ensuring that ML's societal impact aligns with broader social values.

---

### Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents

Authors: Zihao Wang, Xujing Li, Yining Ye, Junjie Fang, Haoming Wang, Longxiang Liu, Shihao Liang, Junting Lu, Zhiyong Wu, Jiazhan Feng, Wanjun Zhong, Zili Li et al.
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23691v1

We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned native keyboard-mouse inputs. Unlike API- or GUI-based approaches, this paradigm enables large-scale continual pre-training across heterogeneous domains, including OS, web, and simulation games. Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data. Key techniques include a decaying continual loss to reduce causal confusion and an efficient Sparse-Thinking strategy that balances reasoning depth and inference cost. Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks, is close to the generality of fresh humans in unseen web 3d games, and outperforms GPT-5, Gemini-2.5-Pro, and Claude-4-Sonnet in FPS benchmarks. Scaling results on training-time and test-time confirm that the unified action space sustains improvements when scaled to cross-game and multimodal data. Our results demonstrate that simple, scalable action representations combined with large-scale pre-training provide a promising path toward generalist agents with broad computer-use abilities.

---

### Parallel BiLSTM-Transformer networks for forecasting chaotic dynamics

Authors: Junwen Ma, Mingyu Ge, Yisen Wang, Yong Zhang, Weicheng Fu
Published: 2025-10-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.23685v1

The nonlinear nature of chaotic systems results in extreme sensitivity to initial conditions and highly intricate dynamical behaviors, posing fundamental challenges for accurately predicting their evolution. To overcome the limitation that conventional approaches fail to capture both local features and global dependencies in chaotic time series simultaneously, this study proposes a parallel predictive framework integrating Transformer and Bidirectional Long Short-Term Memory (BiLSTM) networks. The hybrid model employs a dual-branch architecture, where the Transformer branch mainly captures long-range dependencies while the BiLSTM branch focuses on extracting local temporal features. The complementary representations from the two branches are fused in a dedicated feature-fusion layer to enhance predictive accuracy. As illustrating examples, the model's performance is systematically evaluated on two representative tasks in the Lorenz system. The first is autonomous evolution prediction, in which the model recursively extrapolates system trajectories from the time-delay embeddings of the state vector to evaluate long-term tracking accuracy and stability. The second is inference of unmeasured variable, where the model reconstructs the unobserved states from the time-delay embeddings of partial observations to assess its state-completion capability. The results consistently indicate that the proposed hybrid framework outperforms both single-branch architectures across tasks, demonstrating its robustness and effectiveness in chaotic system prediction.

---

### VIKING: Deep variational inference with stochastic projections

Authors: Samuel G. Fadel, Hrittik Roy, Nicholas Krämer, Yevgen Zainchkovskyy, Stas Syrota, Alejandro Valverde Mahou, Carl Henrik Ek, Søren Hauberg
Published: 2025-10-27
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.23684v1

Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks. Where a Bayesian treatment is usually associated with high-quality predictions and uncertainties, the practical reality has been the opposite, with unstable training, poor predictive power, and subpar calibration. Building upon recent work on reparametrizations of neural networks, we propose a simple variational family that considers two independent linear subspaces of the parameter space. These represent functional changes inside and outside the support of training data. This allows us to build a fully-correlated approximate posterior reflecting the overparametrization that tunes easy-to-interpret hyperparameters. We develop scalable numerical routines that maximize the associated evidence lower bound (ELBO) and sample from the approximate posterior. Empirically, we observe state-of-the-art performance across tasks, models, and datasets compared to a wide array of baseline methods. Our results show that approximate Bayesian inference applied to deep neural networks is far from a lost cause when constructing inference mechanisms that reflect the geometry of reparametrizations.

---

### Beyond Prompt Engineering: Neuro-Symbolic-Causal Architecture for Robust Multi-Objective AI Agents

Authors: Gokturk Aytug Akarlar
Published: 2025-10-27
Categories: cs.LG, cs.AI, cs.LO, cs.SE
arXiv: https://arxiv.org/abs/2510.23682v1

Large language models show promise as autonomous decision-making agents, yet their deployment in high-stakes domains remains fraught with risk. Without architectural safeguards, LLM agents exhibit catastrophic brittleness: identical capabilities produce wildly different outcomes depending solely on prompt framing. We present Chimera, a neuro-symbolic-causal architecture that integrates three complementary components - an LLM strategist, a formally verified symbolic constraint engine, and a causal inference module for counterfactual reasoning. We benchmark Chimera against baseline architectures (LLM-only, LLM with symbolic constraints) across 52-week simulations in a realistic e-commerce environment featuring price elasticity, trust dynamics, and seasonal demand. Under organizational biases toward either volume or margin optimization, LLM-only agents fail catastrophically (total loss of \$99K in volume scenarios) or destroy brand trust (-48.6% in margin scenarios). Adding symbolic constraints prevents disasters but achieves only 43-87% of Chimera's profit. Chimera consistently delivers the highest returns (\$1.52M and \$1.96M respectively, some cases +\$2.2M) while improving brand trust (+1.8% and +10.8%, some cases +20.86%), demonstrating prompt-agnostic robustness. Our TLA+ formal verification proves zero constraint violations across all scenarios. These results establish that architectural design not prompt engineering determines the reliability of autonomous agents in production environments. We provide open-source implementations and interactive demonstrations for reproducibility.

---

### Informed Initialization for Bayesian Optimization and Active Learning

Authors: Carl Hvarfner, David Eriksson, Eytan Bakshy, Max Balandat
Published: 2025-10-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.23681v2

Bayesian Optimization is a widely used method for optimizing expensive black-box functions, relying on probabilistic surrogate models such as Gaussian Processes. The quality of the surrogate model is crucial for good optimization performance, especially in the few-shot setting where only a small number of batches of points can be evaluated. In this setting, the initialization plays a critical role in shaping the surrogate's predictive quality and guiding subsequent optimization. Despite this, practitioners typically rely on (quasi-)random designs to cover the input space. However, such approaches neglect two key factors: (a) space-filling designs may not be desirable to reduce predictive uncertainty, and (b) efficient hyperparameter learning during initialization is essential for high-quality prediction, which may conflict with space-filling designs. To address these limitations, we propose Hyperparameter-Informed Predictive Exploration (HIPE), a novel acquisition strategy that balances predictive uncertainty reduction with hyperparameter learning using information-theoretic principles. We derive a closed-form expression for HIPE in the Gaussian Process setting and demonstrate its effectiveness through extensive experiments in active learning and few-shot BO. Our results show that HIPE outperforms standard initialization strategies in terms of predictive accuracy, hyperparameter identification, and subsequent optimization performance, particularly in large-batch, few-shot settings relevant to many real-world Bayesian Optimization applications.

---

### QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents

Authors: Yuchong Xie, Zesen Liu, Mingyu Luo, Zhixiang Zhang, Kaikai Zhang, Yuanyuan Yuan, Zongjie Li, Ping Chen, Shuai Wang, Dongdong She
Published: 2025-10-27
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.23675v3

Modern coding agents integrated into IDEs orchestrate powerful tools and high-privilege system access, creating a high-stakes attack surface. Prior work on Indirect Prompt Injection (IPI) is mainly query-specific, requiring particular user queries as triggers and leading to poor generalizability. We propose query-agnostic IPI, a new attack paradigm that reliably executes malicious payloads under arbitrary user queries. Our key insight is that malicious payloads should leverage the invariant prompt context (i.e., system prompt and tool descriptions) rather than variant user queries. We present QueryIPI, an automated framework that uses tool descriptions as optimizable payloads and refines them via iterative, prompt-based blackbox optimization. QueryIPI leverages system invariants for initial seed generation aligned with agent conventions, and iterative reflection to resolve instruction-following failures and safety refusals. Experiments on five simulated agents show that QueryIPI achieves up to 87% success rate, outperforming the best baseline (50%). Crucially, generated malicious descriptions transfer to real-world coding agents, highlighting a practical security risk.

---

### RefleXGen:The unexamined code is not worth using

Authors: Bin Wang, Hui Li, AoFan Liu, BoTao Yang, Ao Yang, YiLu Zhong, Weixiang Huang, Yanping Zhang, Runhuai Huang, Weimin Zeng
Published: 2025-10-27
Categories: cs.SE, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.23674v1

Security in code generation remains a pivotal challenge when applying large language models (LLMs). This paper introduces RefleXGen, an innovative method that significantly enhances code security by integrating Retrieval-Augmented Generation (RAG) techniques with guided self-reflection mechanisms inherent in LLMs. Unlike traditional approaches that rely on fine-tuning LLMs or developing specialized secure code datasets - processes that can be resource-intensive - RefleXGen iteratively optimizes the code generation process through self-assessment and reflection without the need for extensive resources. Within this framework, the model continuously accumulates and refines its knowledge base, thereby progressively improving the security of the generated code. Experimental results demonstrate that RefleXGen substantially enhances code security across multiple models, achieving a 13.6% improvement with GPT-3.5 Turbo, a 6.7% improvement with GPT-4o, a 4.5% improvement with CodeQwen, and a 5.8% improvement with Gemini. Our findings highlight that improving the quality of model self-reflection constitutes an effective and practical strategy for strengthening the security of AI-generated code.

---

### MCPGuard : Automatically Detecting Vulnerabilities in MCP Servers

Authors: Bin Wang, Zexin Liu, Hao Yu, Ao Yang, Yenan Huang, Jing Guo, Huangsheng Cheng, Hui Li, Huiyu Wu
Published: 2025-10-27
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.23673v1

The Model Context Protocol (MCP) has emerged as a standardized interface enabling seamless integration between Large Language Models (LLMs) and external data sources and tools. While MCP significantly reduces development complexity and enhances agent capabilities, its openness and extensibility introduce critical security vulnerabilities that threaten system trustworthiness and user data protection. This paper systematically analyzes the security landscape of MCP-based systems, identifying three principal threat categories: (1) agent hijacking attacks stemming from protocol design deficiencies; (2) traditional web vulnerabilities in MCP servers; and (3) supply chain security. To address these challenges, we comprehensively survey existing defense strategies, examining both proactive server-side scanning approaches, ranging from layered detection pipelines and agentic auditing frameworks to zero-trust registry systems, and runtime interaction monitoring solutions that provide continuous oversight and policy enforcement. Our analysis reveals that MCP security fundamentally represents a paradigm shift where the attack surface extends from traditional code execution to semantic interpretation of natural language metadata, necessitating novel defense mechanisms tailored to this unique threat model.

---

### DBLoss: Decomposition-based Loss Function for Time Series Forecasting

Authors: Xiangfei Qiu, Xingjian Wu, Hanyin Cheng, Xvyuan Liu, Chenjuan Guo, Jilin Hu, Bin Yang
Published: 2025-10-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.23672v1

Time series forecasting holds significant value in various domains such as economics, traffic, energy, and AIOps, as accurate predictions facilitate informed decision-making. However, the existing Mean Squared Error (MSE) loss function sometimes fails to accurately capture the seasonality or trend within the forecasting horizon, even when decomposition modules are used in the forward propagation to model the trend and seasonality separately. To address these challenges, we propose a simple yet effective Decomposition-Based Loss function called DBLoss. This method uses exponential moving averages to decompose the time series into seasonal and trend components within the forecasting horizon, and then calculates the loss for each of these components separately, followed by weighting them. As a general loss function, DBLoss can be combined with any deep learning forecasting model. Extensive experiments demonstrate that DBLoss significantly improves the performance of state-of-the-art models across diverse real-world datasets and provides a new perspective on the design of time series loss functions.

---

### Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

Authors: Yujia Zhang, Xiaoyang Wu, Yixing Lao, Chengyao Wang, Zhuotao Tian, Naiyan Wang, Hengshuang Zhao
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23607v2

Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be recalled from a single modality. Inspired by this principle, we introduce Concerto, a minimalist simulation of human concept learning for spatial cognition, combining 3D intra-modal self-distillation with 2D-3D cross-modal joint embedding. Despite its simplicity, Concerto learns more coherent and informative spatial features, as demonstrated by zero-shot visualizations. It outperforms both standalone SOTA 2D and 3D self-supervised models by 14.2% and 4.8%, respectively, as well as their feature concatenation, in linear probing for 3D scene perception. With full fine-tuning, Concerto sets new SOTA results across multiple scene understanding benchmarks (e.g., 80.7% mIoU on ScanNet). We further present a variant of Concerto tailored for video-lifted point cloud spatial understanding, and a translator that linearly projects Concerto representations into CLIP's language space, enabling open-world perception. These results highlight that Concerto emerges spatial representations with superior fine-grained geometric and semantic consistency.

---

### Variational Masked Diffusion Models

Authors: Yichi Zhang, Alex Schwing, Zhizhen Zhao
Published: 2025-10-27
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.23606v1

Masked diffusion models have recently emerged as a flexible framework for discrete generative modeling. However, a key limitation of standard masked diffusion is its inability to effectively capture dependencies among tokens that are predicted concurrently, leading to degraded generation quality when dependencies among tokens are important. To explicitly model dependencies among tokens, we propose Variational Masked Diffusion (VMD), a framework that introduces latent variables into the masked diffusion process. Through controlled experiments on synthetic datasets, we demonstrate that VMD successfully learns dependencies that conventional masked diffusion fails to capture. We further validate the effectiveness of our approach on Sudoku puzzles and text datasets, where learning of dependencies among tokens improves global consistency. Across these domains, VMD enhances both generation quality and dependency awareness, highlighting the value of integrating variational inference into masked diffusion. Our code is available at: https://riccizz.github.io/VMD.

---

### Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling

Authors: Shuhong Zheng, Ashkan Mirzaei, Igor Gilitschenski
Published: 2025-10-27
Categories: cs.CV, cs.AI, cs.GR, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2510.23605v1

Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject across different viewpoints. Adapting generation methods with one or few images of a specific subject (also known as Personalization or Subject-driven generation) allows generating visual content that align with the identity of the subject. However, personalized 3D/4D generation is still largely underexplored. In this work, we introduce TIRE (Track, Inpaint, REsplat), a novel method for subject-driven 3D/4D generation. It takes an initial 3D asset produced by an existing 3D generative model as input and uses video tracking to identify the regions that need to be modified. Then, we adopt a subject-driven 2D inpainting model for progressively infilling the identified regions. Finally, we resplat the modified 2D multi-view observations back to 3D while still maintaining consistency. Extensive experiments demonstrate that our approach significantly improves identity preservation in 3D/4D generation compared to state-of-the-art methods. Our project website is available at https://zsh2000.github.io/track-inpaint-resplat.github.io/.

---

### PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity

Authors: Yuqian Yuan, Wenqiao Zhang, Xin Li, Shihao Wang, Kehan Li, Wentong Li, Jun Xiao, Lei Zhang, Beng Chin Ooi
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23603v2

Multimodal large language models (MLLMs) have demonstrated strong general-purpose capabilities in open-world visual comprehension. However, most existing MLLMs primarily focus on holistic, scene-level understanding, often overlooking the need for fine-grained, object-centric reasoning. In this paper, we present PixelRefer, a unified region-level MLLM framework that enables advanced fine-grained understanding over user-specified regions across both images and videos. Motivated by the observation that LLM attention predominantly focuses on object-level tokens, we propose a Scale-Adaptive Object Tokenizer (SAOT) to generate compact and semantically rich object representations from free-form regions. Our analysis reveals that global visual tokens contribute mainly in early LLM layers, inspiring the design of PixelRefer-Lite, an efficient variant that employs an Object-Centric Infusion module to pre-fuse global context into object tokens. This yields a lightweight Object-Only Framework that substantially reduces computational cost while maintaining high semantic fidelity. To facilitate fine-grained instruction tuning, we curate PixelRefer-2.2M, a high-quality object-centric instruction dataset. Extensive experiments across a range of benchmarks validate that PixelRefer achieves leading performance with fewer training samples, while PixelRefer-Lite offers competitive accuracy with notable gains in efficiency.

---

### Alita-G: Self-Evolving Generative Agent for Agent Generation

Authors: Jiahao Qiu, Xuan Qi, Hongru Wang, Xinzhe Juan, Yimin Wang, Zelin Zhao, Jiayi Geng, Jiacheng Guo, Peihang Li, Jingzhe Shi, Shilong Liu, Mengdi Wang
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23601v1

Large language models (LLMs) have been shown to perform better when scaffolded into agents with memory, tools, and feedback. Beyond this, self-evolving agents have emerged, but current work largely limits adaptation to prompt rewriting or failure retries. Therefore, we present ALITA-G, a self-evolution framework that transforms a general-purpose agent into a domain expert by systematically generating, abstracting, and curating Model Context Protocol (MCP) tools. In this framework, a generalist agent executes a curated suite of target-domain tasks and synthesizes candidate MCPs from successful trajectories. These are then abstracted to parameterized primitives and consolidated into an MCP Box. At inference time, ALITA-G performs retrieval-augmented MCP selection with the help of each tool's descriptions and use cases, before executing an agent equipped with the MCP Executor. Across several benchmarks GAIA, PathVQA, and Humanity's Last Exam, ALITA-G attains strong gains while reducing computation costs. On GAIA validation, it achieves 83.03% pass@1 and 89.09% pass@3, establishing a new state-of-the-art result while reducing mean tokens per example by approximately 15% relative to a strong baseline agent. ALITA-G thus provides a principled pathway from generalist capability to reusable, domain-specific competence, improving both accuracy and efficiency on complex reasoning tasks.

---

### Think Twice: Branch-and-Rethink Reasoning Reward Model

Authors: Yizhu Jiao, Jiaqi Zeng, Julien Veron Vialard, Oleksii Kuchaiev, Jiawei Han, Olivier Delalleau
Published: 2025-10-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.23596v3

Large language models (LLMs) increasingly rely on thinking models that externalize intermediate steps and allocate extra test-time compute, with think-twice strategies showing that a deliberate second pass can elicit stronger reasoning. In contrast, most reward models (RMs) still compress many quality dimensions into a single scalar in one shot, a design that induces judgment diffusion: attention spreads across evaluation criteria, yielding diluted focus and shallow analysis. We introduce branch-and-rethink (BR-RM), a two-turn RM that transfers the think-twice principle to reward modeling. Turn 1 performs adaptive branching, selecting a small set of instance-critical dimensions (such as factuality and safety) and sketching concise, evidence-seeking hypotheses. Turn 2 executes branch-conditioned rethinking, a targeted reread that tests those hypotheses and scrutinizes only what matters most. We train with GRPO-style reinforcement learning over structured two-turn traces using a simple binary outcome reward with strict format checks, making the approach compatible with standard RLHF pipelines. By converting all-at-once scoring into focused, second-look reasoning, BR-RM reduces judgment diffusion and improves sensitivity to subtle yet consequential errors while remaining practical and scalable. Experimental results demonstrate that our model achieves state-of-the-art performance on three challenging reward modeling benchmarks across diverse domains.

---

### Multi-Agent Evolve: LLM Self-Improve through Co-evolution

Authors: Yixing Chen, Yiding Wang, Siqi Zhu, Haofei Yu, Tao Feng, Muhan Zhang, Mostofa Patwary, Jiaxuan You
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23595v3

Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs). However, the success of RL for LLMs heavily relies on human-curated datasets and verifiable rewards, which limit their scalability and generality. Recent Self-Play RL methods, inspired by the success of the paradigm in games and Go, aim to enhance LLM reasoning capabilities without human-annotated data. However, their methods primarily depend on a grounded environment for feedback (e.g., a Python interpreter or a game engine); extending them to general domains remains challenging. To address these challenges, we propose Multi-Agent Evolve (MAE), a framework that enables LLMs to self-evolve in solving diverse tasks, including mathematics, reasoning, and general knowledge Q&A. The core design of MAE is based on a triplet of interacting agents (Proposer, Solver, Judge) that are instantiated from a single LLM, and applies reinforcement learning to optimize their behaviors. The Proposer generates questions, the Solver attempts solutions, and the Judge evaluates both while co-evolving. Experiments on Qwen2.5-3B-Instruct demonstrate that MAE achieves an average improvement of 4.54% on multiple benchmarks. These results highlight MAE as a scalable, data-efficient method for enhancing the general reasoning abilities of LLMs with minimal reliance on human-curated supervision.

---

### PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection

Authors: Yusu Qian, Cheng Wan, Chao Jia, Yinfei Yang, Qingyu Zhao, Zhe Gan
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23594v4

Multimodal large language models (MLLMs) have achieved remarkable progress on vision-language tasks, yet their reasoning processes remain sometimes unreliable. We introduce PRISM-Bench, a benchmark of puzzle-based visual challenges designed to evaluate not only whether models can solve problems, but how their reasoning unfolds. Unlike prior evaluations that measure only final-answer accuracy, PRISM-Bench introduces a diagnostic task: given a visual puzzle and a step-by-step chain-of-thought (CoT) containing exactly one error, models must identify the first incorrect step. This setting enables fine-grained assessment of logical consistency, error detection, and visual reasoning. The puzzles in PRISM-Bench require multi-step symbolic, geometric, and analogical reasoning, resisting shortcuts based on superficial pattern matching. Evaluations across state-of-the-art MLLMs reveal a persistent gap between fluent generation and faithful reasoning: models that produce plausible CoTs often fail to locate simple logical faults. By disentangling answer generation from reasoning verification, PRISM-Bench offers a sharper lens on multimodal reasoning competence and underscores the need for diagnostic evaluation protocols in the development of trustworthy MLLMs.

---

### Lightweight Robust Direct Preference Optimization

Authors: Cheol Woo Kim, Shresth Verma, Mauricio Tec, Milind Tambe
Published: 2025-10-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.23590v1

Direct Preference Optimization (DPO) has become a popular method for fine-tuning large language models (LLMs) due to its stability and simplicity. However, it is also known to be sensitive to noise in the data and prone to overfitting. Recent works have proposed using distributionally robust optimization (DRO) to address potential noise and distributional shift in the data. However, these methods often suffer from excessive conservatism and high computational cost. We propose DPO-PRO (DPO with Preference Robustness), a robust fine-tuning algorithm based on DPO which accounts for uncertainty in the preference distribution through a lightweight DRO formulation. Unlike prior DRO-based variants, DPO-PRO focuses solely on uncertainty in preferences, avoiding unnecessary conservatism and incurring negligible computational overhead. We further show that DPO-PRO is equivalent to a regularized DPO objective that penalizes model overconfidence under weak preference signals. We evaluate DPO-PRO on standard alignment benchmarks and a real-world public health task. Experimental results show that our method consistently improves robustness to noisy preference signals compared to existing DPO variants.

---

### InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras

Authors: Erich Liang, Roma Bhattacharjee, Sreemanti Dey, Rafael Moschopoulos, Caitlin Wang, Michel Liao, Grace Tan, Andrew Wang, Karhan Kayan, Stamatis Alexandropoulos, Jia Deng
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23589v1

Accurately tracking camera intrinsics is crucial for achieving 3D understanding from 2D video. However, most 3D algorithms assume that camera intrinsics stay constant throughout a video, which is often not true for many real-world in-the-wild videos. A major obstacle in this field is a lack of dynamic camera intrinsics benchmarks--existing benchmarks typically offer limited diversity in scene content and intrinsics variation, and none provide per-frame intrinsic changes for consecutive video frames. In this paper, we present Intrinsics in Flux (InFlux), a real-world benchmark that provides per-frame ground truth intrinsics annotations for videos with dynamic intrinsics. Compared to prior benchmarks, InFlux captures a wider range of intrinsic variations and scene diversity, featuring 143K+ annotated frames from 386 high-resolution indoor and outdoor videos with dynamic camera intrinsics. To ensure accurate per-frame intrinsics, we build a comprehensive lookup table of calibration experiments and extend the Kalibr toolbox to improve its accuracy and robustness. Using our benchmark, we evaluate existing baseline methods for predicting camera intrinsics and find that most struggle to achieve accurate predictions on videos with dynamic intrinsics. For the dataset, code, videos, and submission, please visit https://influx.cs.princeton.edu/.

---

### FARMER: Flow AutoRegressive Transformer over Pixels

Authors: Guangting Zheng, Qinyu Zhao, Tao Yang, Fei Xiao, Zhijie Lin, Jie Wu, Jiajun Deng, Yanyong Zhang, Rui Zhu
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23588v2

Directly modeling the explicit likelihood of the raw data distribution is key topic in the machine learning area, which achieves the scaling successes in Large Language Models by autoregressive modeling. However, continuous AR modeling over visual pixel data suffer from extremely long sequences and high-dimensional spaces. In this paper, we present FARMER, a novel end-to-end generative framework that unifies Normalizing Flows (NF) and Autoregressive (AR) models for tractable likelihood estimation and high-quality image synthesis directly from raw pixels. FARMER employs an invertible autoregressive flow to transform images into latent sequences, whose distribution is modeled implicitly by an autoregressive model. To address the redundancy and complexity in pixel-level modeling, we propose a self-supervised dimension reduction scheme that partitions NF latent channels into informative and redundant groups, enabling more effective and efficient AR modeling. Furthermore, we design a one-step distillation scheme to significantly accelerate inference speed and introduce a resampling-based classifier-free guidance algorithm to boost image generation quality. Extensive experiments demonstrate that FARMER achieves competitive performance compared to existing pixel-based generative models while providing exact likelihoods and scalable training.

---

### A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

Authors: Yizhang Zhu, Liangwei Wang, Chenyu Yang, Xiaotian Lin, Boyan Li, Wei Zhou, Xinyu Liu, Zhangyang Peng, Tianqi Luo, Yu Li, Chengliang Chai, Chong Chen et al.
Published: 2025-10-27
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2510.23587v2

The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex data-related tasks. However, the term "data agent" currently suffers from terminological ambiguity and inconsistent adoption, conflating simple query responders with sophisticated autonomous architectures. This terminological ambiguity fosters mismatched user expectations, accountability challenges, and barriers to industry growth. Inspired by the SAE J3016 standard for driving automation, this survey introduces the first systematic hierarchical taxonomy for data agents, comprising six levels that delineate and trace progressive shifts in autonomy, from manual operations (L0) to a vision of generative, fully autonomous data agents (L5), thereby clarifying capability boundaries and responsibility allocation. Through this lens, we offer a structured review of existing research arranged by increasing autonomy, encompassing specialized data agents for data management, preparation, and analysis, alongside emerging efforts toward versatile, comprehensive systems with enhanced autonomy. We further analyze critical evolutionary leaps and technical gaps for advancing data agents, especially the ongoing L2-to-L3 transition, where data agents evolve from procedural execution to autonomous orchestration. Finally, we conclude with a forward-looking roadmap, envisioning proactive, generative data agents.

---

### Hope Speech Detection in Social Media English Corpora: Performance of Traditional and Transformer Models

Authors: Luis Ramos, Hiram Calvo, Olga Kolesnikova
Published: 2025-10-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.23585v1

The identification of hope speech has become a promised NLP task, considering the need to detect motivational expressions of agency and goal-directed behaviour on social media platforms. This proposal evaluates traditional machine learning models and fine-tuned transformers for a previously split hope speech dataset as train, development and test set. On development test, a linear-kernel SVM and logistic regression both reached a macro-F1 of 0.78; SVM with RBF kernel reached 0.77, and Naïve Bayes hit 0.75. Transformer models delivered better results, the best model achieved weighted precision of 0.82, weighted recall of 0.80, weighted F1 of 0.79, macro F1 of 0.79, and 0.80 accuracy. These results suggest that while optimally configured traditional machine learning models remain agile, transformer architectures detect some subtle semantics of hope to achieve higher precision and recall in hope speech detection, suggesting that larges transformers and LLMs could perform better in small datasets.

---

### Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation

Authors: Junyoung Seo, Rodrigo Mira, Alexandros Haliassos, Stella Bounareli, Honglie Chen, Linh Tran, Seungryong Kim, Zoe Landgraf, Jie Shen
Published: 2025-10-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.23581v1

Audio-driven human animation models often suffer from identity drift during temporal autoregressive generation, where characters gradually lose their identity over time. One solution is to generate keyframes as intermediate temporal anchors that prevent degradation, but this requires an additional keyframe generation stage and can restrict natural motion dynamics. To address this, we propose Lookahead Anchoring, which leverages keyframes from future timesteps ahead of the current generation window, rather than within it. This transforms keyframes from fixed boundaries into directional beacons: the model continuously pursues these future anchors while responding to immediate audio cues, maintaining consistent identity through persistent guidance. This also enables self-keyframing, where the reference image serves as the lookahead target, eliminating the need for keyframe generation entirely. We find that the temporal lookahead distance naturally controls the balance between expressivity and consistency: larger distances allow for greater motion freedom, while smaller ones strengthen identity adherence. When applied to three recent human animation models, Lookahead Anchoring achieves superior lip synchronization, identity preservation, and visual quality, demonstrating improved temporal conditioning across several different architectures. Video results are available at the following link: https://lookahead-anchoring.github.io.

---

### Reduced AI Acceptance After the Generative AI Boom: Evidence From a Two-Wave Survey Study

Authors: Joachim Baumann, Aleksandra Urman, Ulrich Leicht-Deobald, Zachary J. Roman, Anikó Hannák, Markus Christen
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23578v1

The rapid adoption of generative artificial intelligence (GenAI) technologies has led many organizations to integrate AI into their products and services, often without considering user preferences. Yet, public attitudes toward AI use, especially in impactful decision-making scenarios, are underexplored. Using a large-scale two-wave survey study (n_wave1=1514, n_wave2=1488) representative of the Swiss population, we examine shifts in public attitudes toward AI before and after the launch of ChatGPT. We find that the GenAI boom is significantly associated with reduced public acceptance of AI (see Figure 1) and increased demand for human oversight in various decision-making contexts. The proportion of respondents finding AI "not acceptable at all" increased from 23% to 30%, while support for human-only decision-making rose from 18% to 26%. These shifts have amplified existing social inequalities in terms of widened educational, linguistic, and gender gaps post-boom. Our findings challenge industry assumptions about public readiness for AI deployment and highlight the critical importance of aligning technological development with evolving public preferences.

---

### UrbanVLA: A Vision-Language-Action Model for Urban Micromobility

Authors: Anqi Li, Zhiyong Wang, Jiazhao Zhang, Minghan Li, Yunpeng Qi, Zhibo Chen, Zhizheng Zhang, He Wang
Published: 2025-10-27
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.23576v2

Urban micromobility applications, such as delivery robots, demand reliable navigation across large-scale urban environments while following long-horizon route instructions. This task is particularly challenging due to the dynamic and unstructured nature of real-world city areas, yet most existing navigation methods remain tailored to short-scale and controllable scenarios. Effective urban micromobility requires two complementary levels of navigation skills: low-level capabilities such as point-goal reaching and obstacle avoidance, and high-level capabilities, such as route-visual alignment. To this end, we propose UrbanVLA, a route-conditioned Vision-Language-Action (VLA) framework designed for scalable urban navigation. Our method explicitly aligns noisy route waypoints with visual observations during execution, and subsequently plans trajectories to drive the robot. To enable UrbanVLA to master both levels of navigation, we employ a two-stage training pipeline. The process begins with Supervised Fine-Tuning (SFT) using simulated environments and trajectories parsed from web videos. This is followed by Reinforcement Fine-Tuning (RFT) on a mixture of simulation and real-world data, which enhances the model's safety and adaptability in real-world settings. Experiments demonstrate that UrbanVLA surpasses strong baselines by more than 55% in the SocialNav task on MetaUrban. Furthermore, UrbanVLA achieves reliable real-world navigation, showcasing both scalability to large-scale urban environments and robustness against real-world uncertainties.

---

### More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models

Authors: Hongkai Lin, Dingkang Liang, Mingyang Du, Xin Zhou, Xiang Bai
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23574v1

Generative depth estimation methods leverage the rich visual priors stored in pre-trained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, parameter updates during training lead to catastrophic degradation in the image generation capability of the pre-trained model. We introduce MERGE, a unified model for image generation and depth estimation, starting from a fixed pre-trained text-to-image model. MERGE demonstrates that the pre-trained text-to-image model can do more than image generation, but also expand to depth estimation effortlessly. Specifically, MERGE introduces a play-and-plug framework that enables seamless switching between image generation and depth estimation modes through simple and pluggable converters. Meanwhile, we propose a Group Reuse Mechanism to encourage parameter reuse and improve the utilization of the additional learnable parameters. MERGE unleashes the powerful depth estimation capability of the pre-trained text-to-image model while preserving its original image generation ability. Compared to other unified models for image generation and depth estimation, MERGE achieves state-of-the-art performance across multiple depth estimation benchmarks. The code will be made available at https://github.com/H-EmbodVis/MERGE

---

### RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation

Authors: Yash Jangir, Yidi Zhang, Pang-Chi Lo, Kashu Yamazaki, Chenyu Zhang, Kuan-Hsun Tu, Tsung-Wei Ke, Lei Ke, Yonatan Bisk, Katerina Fragkiadaki
Published: 2025-10-27
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.23571v3

The pursuit of robot generalists, agents capable of performing diverse tasks across diverse environments, demands rigorous and scalable evaluation. Yet real-world testing of robot policies remains fundamentally constrained: it is labor-intensive, slow, unsafe at scale, and difficult to reproduce. As policies expand in scope and complexity, these barriers only intensify, since defining "success" in robotics often hinges on nuanced human judgments of execution quality. We introduce RobotArena Infinity, a new benchmarking framework that overcomes these challenges by shifting vision-language-action (VLA) evaluation into large-scale simulated environments augmented with online human feedback. Leveraging advances in vision-language models, 2D-to-3D generative modeling, and differentiable rendering, our approach automatically converts video demonstrations from widely used robot datasets into simulated counterparts. Within these digital twins, we assess VLA policies using both automated vision-language-model-guided scoring and scalable human preference judgments collected from crowdworkers, transforming human involvement from tedious scene setup, resetting, and safety supervision into lightweight preference comparisons. To measure robustness, we systematically perturb simulated environments along multiple axes, including textures and object placements, stress-testing policy generalization under controlled variation. The result is a continuously evolving, reproducible, and scalable benchmark for real-world-trained robot manipulation policies, addressing a critical missing capability in today's robotics landscape.

---

### EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT

Authors: Baoqi Pei, Yifei Huang, Jilan Xu, Yuping He, Guo Chen, Fei Wu, Yu Qiao, Jiangmiao Pang
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23569v1

Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fine-grained interactions. This core challenge limits current multimodal large language models MLLMs, which excel at visible event reasoning but lack embodied, first-person understanding. To bridge this gap, we introduce EgoThinker, a novel framework that endows MLLMs with robust egocentric reasoning capabilities through spatio-temporal chain-of-thought supervision and a two-stage learning curriculum. First, we introduce EgoRe-5M, a large-scale egocentric QA dataset constructed from 13M diverse egocentric video clips. This dataset features multi-minute segments annotated with detailed CoT rationales and dense hand-object grounding. Second, we employ SFT on EgoRe-5M to instill reasoning skills, followed by reinforcement fine-tuning RFT to further enhance spatio-temporal localization. Experimental results show that EgoThinker outperforms existing methods across multiple egocentric benchmarks, while achieving substantial improvements in fine-grained spatio-temporal localization tasks. Full code and data are released at https://github.com/InternRobotics/EgoThinker.

---

### ReCode: Unify Plan and Action for Universal Granularity Control

Authors: Zhaoyang Yu, Jiayi Zhang, Huixue Su, Yufan Zhao, Yifan Wu, Mingyi Deng, Jinyu Xiang, Yizhang Lin, Lingxiao Tang, Yuyu Luo, Bang Liu, Chenglin Wu
Published: 2025-10-27
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.23564v4

Real-world tasks require decisions at varying granularities, and humans excel at this by leveraging a unified cognitive representation where planning is fundamentally understood as a high-level form of action. However, current Large Language Model (LLM)-based agents lack this crucial capability to operate fluidly across decision granularities. This limitation stems from existing paradigms that enforce a rigid separation between high-level planning and low-level action, which impairs dynamic adaptability and limits generalization. We propose ReCode (Recursive Code Generation), a novel paradigm that addresses this limitation by unifying planning and action within a single code representation. In this representation, ReCode treats high-level plans as abstract placeholder functions, which the agent then recursively decomposes into finer-grained sub-functions until reaching primitive actions. This recursive approach dissolves the rigid boundary between plan and action, enabling the agent to dynamically control its decision granularity. Furthermore, the recursive structure inherently generates rich, multi-granularity training data, enabling models to learn hierarchical decision-making processes. Extensive experiments show ReCode significantly surpasses advanced baselines in inference performance and demonstrates exceptional data efficiency in training, validating our core insight that unifying planning and action through recursive code generation is a powerful and effective approach to achieving universal granularity control. The code is available at https://github.com/FoundationAgents/ReCode.

---

### Revising Second Order Terms in Deep Animation Video Coding

Authors: Konstantin Schmidt, Thomas Richter
Published: 2025-10-27
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2510.23561v1

First Order Motion Model is a generative model that animates human heads based on very little motion information derived from keypoints. It is a promising solution for video communication because first it operates at very low bitrate and second its computational complexity is moderate compared to other learning based video codecs. However, it has strong limitations by design. Since it generates facial animations by warping source-images, it fails to recreate videos with strong head movements. This works concentrates on one specific kind of head movements, namely head rotations. We show that replacing the Jacobian transformations in FOMM by a global rotation helps the system to perform better on items with head-rotations while saving 40% to 80% of bitrate on P-frames. Moreover, we apply state-of-the-art normalization techniques to the discriminator to stabilize the adversarial training which is essential for generating visually appealing videos. We evaluate the performance by the learned metics LPIPS and DISTS to show the success our optimizations.

---

### ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models

Authors: Bohan Li, Wenbin Huang, Yuhang Qiu, Yiwei Guo, Hankun Wang, Zhihan Li, Jing Peng, Ziyang Ma, Xie Chen, Kai Yu
Published: 2025-10-27
Categories: cs.SD, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2510.23558v1

Large Audio Language Models (LALMs), which couple acoustic perception with large language models (LLMs) to extract and understand diverse information from audio, have attracted intense interest from both academic and industrial communities. However, existing LALMs are highly sensitive to how instructions are phrased, affecting both (i) instruction-following rates and (ii) task performance. Yet, no existing benchmarks offer a systematic and comprehensive evaluation of this sensitivity. We introduce ISA-Bench, a dynamic benchmark evaluating instruction sensitivity for LALMs along three axes: instruction description, output format, and task composition. We assess recent open-source and proprietary LALMs using ISA-Bench, profiling both compliance and accuracy under controlled instruction variations. Experimental results reveal that even state-of-the-art LALMs suffer significant instruction sensitivity, leading to degraded performance on fundamental audio understanding tasks. To mitigate this issue, we fine-tune Qwen2-Audio on a specifically constructed complex instruction-variant dataset, achieving a marked improvement in instruction-following performance. However, this also induces nontrivial catastrophic forgetting: the model loses some previously mastered task capabilities when exposed to new instruction styles. Our benchmark provides a standardized basis for assessing and improving instruction sensitivity in LALMs, underscoring the need for instruction-robust audio understanding in real-world pipelines.

---

### Minimizing Human Intervention in Online Classification

Authors: William Réveillard, Vasileios Saketos, Alexandre Proutiere, Richard Combes
Published: 2025-10-27
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.23557v2

Training or fine-tuning large language model (LLM)-based systems often requires costly human feedback, yet there is limited understanding of how to minimize such intervention while maintaining strong error guarantees. We study this problem for LLM-based classification systems in an active learning framework: an agent sequentially labels $d$-dimensional query embeddings drawn i.i.d. from an unknown distribution by either calling a costly expert or guessing with no feedback, with the goal of minimizing regret relative to an oracle with free expert access. When the horizon $T$ is at least exponential in the embedding dimension $d$, the geometry of the class regions can be learned. In this regime, we propose the Conservative Hull-based Classifier (CHC), which maintains convex hulls of expert-labeled queries and calls the expert when a query lands outside all known hulls. CHC attains $\mathcal{O}(\log^d T)$ regret in $T$ and is minimax optimal for $d=1$. Otherwise, the geometry cannot be reliably learned in general. We show that for queries drawn from a subgaussian mixture and $T \le e^d$, a Center-based Classifier (CC) achieves regret proportional to $N\log{N}$ where $N$ is the number of labels. To bridge these regimes, we introduce the Generalized Hull-based Classifier (GHC), a practical extension of CHC that enables more aggressive guessing via a tunable parameter. Our approach is validated on real-world question-answering datasets using state-of-the-art text embedding models.

---

### A U-Net and Transformer Pipeline for Multilingual Image Translation

Authors: Siddharth Sahay, Radhika Agarwal
Published: 2025-10-27
Categories: cs.LG, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.23554v1

This paper presents an end-to-end multilingual translation pipeline that integrates a custom U-Net for text detection, the Tesseract engine for text recognition, and a from-scratch sequence-to-sequence (Seq2Seq) Transformer for Neural Machine Translation (NMT). Our approach first utilizes a U-Net model, trained on a synthetic dataset , to accurately segment and detect text regions from an image. These detected regions are then processed by Tesseract to extract the source text. This extracted text is fed into a custom Transformer model trained from scratch on a multilingual parallel corpus spanning 5 languages. Unlike systems reliant on monolithic pre-trained models, our architecture emphasizes full customization and adaptability. The system is evaluated on its text detection accuracy, text recognition quality, and translation performance via BLEU scores. The complete pipeline demonstrates promising results, validating the viability of a custom-built system for translating text directly from images.

---

### OntoPret: An Ontology for the Interpretation of Human Behavior

Authors: Alexis Ellis, Stacie Severyn, Fjollë Novakazi, Hadi Banaee, Cogan Shimizu
Published: 2025-10-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.23553v1

As human machine teaming becomes central to paradigms like Industry 5.0, a critical need arises for machines to safely and effectively interpret complex human behaviors. A research gap currently exists between techno centric robotic frameworks, which often lack nuanced models of human behavior, and descriptive behavioral ontologies, which are not designed for real time, collaborative interpretation. This paper addresses this gap by presenting OntoPret, an ontology for the interpretation of human behavior. Grounded in cognitive science and a modular engineering methodology, OntoPret provides a formal, machine processable framework for classifying behaviors, including task deviations and deceptive actions. We demonstrate its adaptability across two distinct use cases manufacturing and gameplay and establish the semantic foundations necessary for advanced reasoning about human intentions.

---

### Bayesian Nonlinear PDE Inference via Gaussian Process Collocation with Application to the Richards Equation

Authors: Yumo Yang, Anass Ben Bouazza, Xuejun Dong, Quan Zhou
Published: 2025-10-27
Categories: stat.ME, stat.AP, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2510.23550v1

The estimation of unknown parameters in nonlinear partial differential equations (PDEs) offers valuable insights across a wide range of scientific domains. In this work, we focus on estimating plant root parameters in the Richards equation, which is essential for understanding the soil-plant system in agricultural studies. Since conventional methods are computationally intensive and often yield unstable estimates, we develop a new Gaussian process collocation method for efficient Bayesian inference. Unlike existing Gaussian process-based approaches, our method constructs an approximate posterior distribution using samples drawn from a Gaussian process model fitted to the observed data, which does not require any structural assumption about the underlying PDE. Further, we propose to use an importance sampling procedure to correct for the discrepancy between the approximate and true posterior distributions. As an alternative, we also devise a prior-guided Bayesian optimization algorithm leveraging the approximate posterior. Simulation studies demonstrate that our method yields robust estimates under various settings. Finally, we apply our method on a real agricultural data set and estimate the plant root parameters with uncertainty quantification.

---

### LimRank: Less is More for Reasoning-Intensive Information Reranking

Authors: Tingyu Song, Yilun Zhao, Siyue Zhang, Chen Zhao, Arman Cohan
Published: 2025-10-27
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.23544v1

Existing approaches typically rely on large-scale fine-tuning to adapt LLMs for information reranking tasks, which is computationally expensive. In this work, we demonstrate that modern LLMs can be effectively adapted using only minimal, high-quality supervision. To enable this, we design LIMRANK-SYNTHESIZER, a reusable and open-source pipeline for generating diverse, challenging, and realistic reranking examples. Using this synthetic data, we fine-tune our reranker model, LIMRANK. We evaluate LIMRANK on two challenging benchmarks, i.e., BRIGHT for reasoning-intensive retrieval and FollowIR for instruction-following retrieval. Our experiments demonstrate that LIMRANK achieves competitive performance, while being trained on less than 5% of the data typically used in prior work. Further ablation studies demonstrate the effectiveness of LIMRANK-SYNTHESIZER and the strong generalization capabilities of LIMRANK across downstream tasks, including scientific literature search and retrieval-augmented generation for knowledge-intensive problem solving.

---

### JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

Authors: Qiushi Sun, Jingyang Gong, Yang Liu, Qiaosheng Chen, Lei Li, Kai Chen, Qipeng Guo, Ben Kao, Fei Yuan
Published: 2025-10-27
Categories: cs.AI, cs.CL, cs.CV, cs.SE
arXiv: https://arxiv.org/abs/2510.23538v3

The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate. This visual dimension is critical for advanced applications like flexible content generation and precise, program-driven editing of visualizations. However, progress has been impeded by the scarcity of high-quality multimodal code data, a bottleneck stemming from challenges in synthesis and quality assessment. To address these challenges, we make contributions from both a data and modeling perspective. We first introduce a complete synthesis toolkit that leverages reciprocal synergies between data modalities to efficiently produce a large-scale, high-quality corpus spanning from standard charts to complex interactive web UIs and code-driven animations. Leveraging this toolkit, we construct JanusCode-800K, the largest multimodal code corpus to date. This powers the training of our models, JanusCoder and JanusCoderV, which establish a visual-programmatic interface for generating code from textual instructions, visual inputs, or a combination of both. Our unified model is a departure from existing approaches that build specialized models for isolated tasks. Extensive experiments on both text-centric and vision-centric coding tasks demonstrate the superior performance of the JanusCoder series, with our 7B to 14B scale models approaching or even exceeding the performance of commercial models. Furthermore, extensive analysis provides key insights into harmonizing programmatic logic with its visual expression. Our code and checkpoints are available at https://github.com/InternLM/JanusCoder.

---

### IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering

Authors: Jieyong Kim, Maryam Amirizaniani, Soojin Yoon, Dongha Lee
Published: 2025-10-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.23536v2

Intent identification serves as the foundation for generating appropriate responses in personalized question answering (PQA). However, existing benchmarks evaluate only response quality or retrieval performance without directly measuring intent identification capabilities. This gap is critical because without understanding which intents users prioritize, systems cannot generate responses satisfying individual information needs. To address this, we introduce the concept of core intents: intents users prioritize when selecting answers to satisfy their information needs. To evaluate these core intents, we propose IPQA, a benchmark for core Intent identification in Personalized Question Answering. Since users do not explicitly state their prioritized intents, we derive core intents from observable behavior patterns in answer selection, grounded in satisficing theory where users choose answers meeting their acceptance thresholds. We construct a dataset with various domains through systematic filtering, LLM-based annotation, and rigorous quality control combining automated verification with human validation. Experimental evaluations across state-of-the-art language models reveal that current systems struggle with core intent identification in personalized contexts. Models fail to identify core intents from user histories, with performance degrading as question complexity increases. The code and dataset will be made publicly available to facilitate future research in this direction.

---

### Sequential Multi-Agent Dynamic Algorithm Configuration

Authors: Chen Lu, Ke Xue, Lei Yuan, Yao Wang, Yaoyuan Wang, Sheng Fu, Chao Qian
Published: 2025-10-27
Categories: cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2510.23535v1

Dynamic algorithm configuration (DAC) is a recent trend in automated machine learning, which can dynamically adjust the algorithm's configuration during the execution process and relieve users from tedious trial-and-error tuning tasks. Recently, multi-agent reinforcement learning (MARL) approaches have improved the configuration of multiple heterogeneous hyperparameters, making various parameter configurations for complex algorithms possible. However, many complex algorithms have inherent inter-dependencies among multiple parameters (e.g., determining the operator type first and then the operator's parameter), which are, however, not considered in previous approaches, thus leading to sub-optimal results. In this paper, we propose the sequential multi-agent DAC (Seq-MADAC) framework to address this issue by considering the inherent inter-dependencies of multiple parameters. Specifically, we propose a sequential advantage decomposition network, which can leverage action-order information through sequential advantage decomposition. Experiments from synthetic functions to the configuration of multi-objective optimization algorithms demonstrate Seq-MADAC's superior performance over state-of-the-art MARL methods and show strong generalization across problem classes. Seq-MADAC establishes a new paradigm for the widespread dependency-aware automated algorithm configuration. Our code is available at https://github.com/lamda-bbo/seq-madac.

---

### Direct Debiased Machine Learning via Bregman Divergence Minimization

Authors: Masahiro Kato
Published: 2025-10-27
Categories: econ.EM, cs.LG, math.ST, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.23534v2

We develop a direct debiased machine learning framework comprising Neyman targeted estimation and generalized Riesz regression. Our framework unifies Riesz regression for automatic debiased machine learning, covariate balancing, targeted maximum likelihood estimation (TMLE), and density-ratio estimation. In many problems involving causal effects or structural models, the parameters of interest depend on regression functions. Plugging regression functions estimated by machine learning methods into the identifying equations can yield poor performance because of first-stage bias. To reduce such bias, debiased machine learning employs Neyman orthogonal estimating equations. Debiased machine learning typically requires estimation of the Riesz representer and the regression function. For this problem, we develop a direct debiased machine learning framework with an end-to-end algorithm. We formulate estimation of the nuisance parameters, the regression function and the Riesz representer, as minimizing the discrepancy between Neyman orthogonal scores computed with known and unknown nuisance parameters, which we refer to as Neyman targeted estimation. Neyman targeted estimation includes Riesz representer estimation, and we measure discrepancies using the Bregman divergence. The Bregman divergence encompasses various loss functions as special cases, where the squared loss yields Riesz regression and the Kullback-Leibler divergence yields entropy balancing. We refer to this Riesz representer estimation as generalized Riesz regression. Neyman targeted estimation also yields TMLE as a special case for regression function estimation. Furthermore, for specific pairs of models and Riesz representer estimation methods, we can automatically obtain the covariate balancing property without explicitly solving the covariate balancing objective.

---

### When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning

Authors: Anirban Das, Irtaza Khalid, Rafael Peñaloza, Steven Schockaert
Published: 2025-10-27
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.23532v1

Designing models that can learn to reason in a systematic way is an important and long-standing challenge. In recent years, a wide range of solutions have been proposed for the specific case of systematic relational reasoning, including Neuro-Symbolic approaches, variants of the Transformer architecture, and specialised Graph Neural Networks. However, existing benchmarks for systematic relational reasoning focus on an overly simplified setting, based on the assumption that reasoning can be reduced to composing relational paths. In fact, this assumption is hard-baked into the architecture of several recent models, leading to approaches that can perform well on existing benchmarks but are difficult to generalise to other settings. To support further progress in the field of systematic relational reasoning with neural networks, we introduce NoRA, a new benchmark which adds several levels of difficulty and requires models to go beyond path-based reasoning.

---

### Learning Linearity in Audio Consistency Autoencoders via Implicit Regularization

Authors: Bernardo Torres, Manuel Moussallam, Gabriel Meseguer-Brocal
Published: 2025-10-27
Categories: cs.SD, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.23530v2

Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introduce a simple training methodology to induce linearity in a high-compression Consistency Autoencoder (CAE) by using data augmentation, thereby inducing homogeneity (equivariance to scalar gain) and additivity (the decoder preserves addition) without altering the model's architecture or loss function. When trained with our method, the CAE exhibits linear behavior in both the encoder and decoder while preserving reconstruction fidelity. We test the practical utility of our learned space on music source composition and separation via simple latent arithmetic. This work presents a straightforward technique for constructing structured latent spaces, enabling more intuitive and efficient audio processing.

---

### DPGLA: Bridging the Gap between Synthetic and Real Data for Unsupervised Domain Adaptation in 3D LiDAR Semantic Segmentation

Authors: Wanmeng Li, Simone Mosco, Daniel Fusaro, Alberto Pretto
Published: 2025-10-27
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.23525v1

Annotating real-world LiDAR point clouds for use in intelligent autonomous systems is costly. To overcome this limitation, self-training-based Unsupervised Domain Adaptation (UDA) has been widely used to improve point cloud semantic segmentation by leveraging synthetic point cloud data. However, we argue that existing methods do not effectively utilize unlabeled data, as they either rely on predefined or fixed confidence thresholds, resulting in suboptimal performance. In this paper, we propose a Dynamic Pseudo-Label Filtering (DPLF) scheme to enhance real data utilization in point cloud UDA semantic segmentation. Additionally, we design a simple and efficient Prior-Guided Data Augmentation Pipeline (PG-DAP) to mitigate domain shift between synthetic and real-world point clouds. Finally, we utilize data mixing consistency loss to push the model to learn context-free representations. We implement and thoroughly evaluate our approach through extensive comparisons with state-of-the-art methods. Experiments on two challenging synthetic-to-real point cloud semantic segmentation tasks demonstrate that our approach achieves superior performance. Ablation studies confirm the effectiveness of the DPLF and PG-DAP modules. We release the code of our method in this paper.

---

### Toward Carbon-Neutral Human AI: Rethinking Data, Computation, and Learning Paradigms for Sustainable Intelligence

Authors: KC Santosh, Rodrigue Rizk, Longwei Wang
Published: 2025-10-27
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.23524v1

The rapid advancement of Artificial Intelligence (AI) has led to unprecedented computational demands, raising significant environmental and ethical concerns. This paper critiques the prevailing reliance on large-scale, static datasets and monolithic training paradigms, advocating for a shift toward human-inspired, sustainable AI solutions. We introduce a novel framework, Human AI (HAI), which emphasizes incremental learning, carbon-aware optimization, and human-in-the-loop collaboration to enhance adaptability, efficiency, and accountability. By drawing parallels with biological cognition and leveraging dynamic architectures, HAI seeks to balance performance with ecological responsibility. We detail the theoretical foundations, system design, and operational principles that enable AI to learn continuously and contextually while minimizing carbon footprints and human annotation costs. Our approach addresses pressing challenges in active learning, continual adaptation, and energy-efficient model deployment, offering a pathway toward responsible, human-centered artificial intelligence.

---

### FreeFuse: Multi-Subject LoRA Fusion via Adaptive Token-Level Routing at Test Time

Authors: Yaoli Liu, Yao-Xiang Ding, Kun Zhou
Published: 2025-10-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.23515v3

This paper proposes FreeFuse, a training-free framework for multi-subject text-to-image generation through automatic fusion of multiple subject LoRAs. In contrast to prior studies that focus on retraining LoRAs to alleviate feature conflicts, our analysis shows that spatially routing LoRA residuals to their intended semantic regions provides an effective mechanism for suppressing direct cross-region LoRA interference while preserving the base model's global contextual reasoning. Accordingly, we implement Adaptive Token-Level Routing during the inference phase. However, obtaining reliable routing regions remains challenging. Existing methods that rely on text-image latent association, such as raw cross-attention or concept-level similarity matching, often suffer from sparse activations, hole artifacts, and unstable localization when handling visually similar subjects, leading to incomplete or ambiguous subject masks. To address these issues, we introduce FreeFuseAttn, a mechanism that exploits the flow matching model's intrinsic semantic alignment to dynamically match subject-specific tokens to their corresponding spatial regions at early denoising timesteps, thereby bypassing the need for external segmentors. FreeFuse distinguishes itself through high practicality: it necessitates no additional training, model modifications, or user-defined spatial constraints. Users need only provide subject activation words to achieve seamless integration into standard workflows. Extensive experiments validate that FreeFuse outperforms existing approaches in both identity preservation and compositional fidelity. The project page is at: https://future-item.github.io/FreeFuse/.

---