# Research Papers — 2026-01 · bundle page 152 of 189

> Full-text markdown of papers #7551–7600 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/152
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/151.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/153.md)

### Forge-and-Quench: Enhancing Image Generation for Higher Fidelity in Unified Multimodal Models

Authors: Yanbing Zeng, Jia Wang, Hanghang Ma, Junqiang Wu, Jie Zhu, Xiaoming Wei, Jie Hu
Published: 2026-01-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.04706v1

Integrating image generation and understanding into a single framework has become a pivotal goal in the multimodal domain. However, how understanding can effectively assist generation has not been fully explored. Unlike previous works that focus on leveraging reasoning abilities and world knowledge from understanding models, this paper introduces a novel perspective: leveraging understanding to enhance the fidelity and detail richness of generated images. To this end, we propose Forge-and-Quench, a new unified framework that puts this principle into practice. In the generation process of our framework, an MLLM first reasons over the entire conversational context, including text instructions, to produce an enhanced text instruction. This refined instruction is then mapped to a virtual visual representation, termed the Bridge Feature, via a novel Bridge Adapter. This feature acts as a crucial link, forging insights from the understanding model to quench and refine the generation process. It is subsequently injected into the T2I backbone as a visual guidance signal, alongside the enhanced text instruction that replaces the original input. To validate this paradigm, we conduct comprehensive studies on the design of the Bridge Feature and Bridge Adapter. Our framework demonstrates exceptional extensibility and flexibility, enabling efficient migration across different MLLM and T2I models with significant savings in training overhead, all without compromising the MLLM's inherent multimodal understanding capabilities. Experiments show that Forge-and-Quench significantly improves image fidelity and detail across multiple models, while also maintaining instruction-following accuracy and enhancing world knowledge application. Models and codes are available at https://github.com/YanbingZeng/Forge-and-Quench.

---

### A zone-based training approach for last-mile routing using Graph Neural Networks and Pointer Networks

Authors: Àngel Ruiz-Fas, Carlos Granell, José Francisco Ramos, Joaquín Huerta, Sergio Trilles
Published: 2026-01-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.04705v1

Rapid e-commerce growth has pushed last-mile delivery networks to their limits, where small routing gains translate into lower costs, faster service, and fewer emissions. Classical heuristics struggle to adapt when travel times are highly asymmetric (e.g., one-way streets, congestion). A deep learning-based approach to the last-mile routing problem is presented to generate geographical zones composed of stop sequences to minimize last-mile delivery times. The presented approach is an encoder-decoder architecture. Each route is represented as a complete directed graph whose nodes are stops and whose edge weights are asymmetric travel times. A Graph Neural Network encoder produces node embeddings that captures the spatial relationships between stops. A Pointer Network decoder then takes the embeddings and the route's start node to sequentially select the next stops, assigning a probability to each unvisited node as the next destination. Cells of a Discrete Global Grid System which contain route stops in the training data are obtained and clustered to generate geographical zones of similar size in which the process of training and inference are divided. Subsequently, a different instance of the model is trained per zone only considering the stops of the training routes which are included in that zone. This approach is evaluated using the Los Angeles routes from the 2021 Amazon Last Mile Routing Challenge. Results from general and zone-based training are compared, showing a reduction in the average predicted route length in the zone-based training compared to the general training. The performance improvement of the zone-based approach becomes more pronounced as the number of stops per route increases.

---

### Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search

Authors: Yiqun Chen, Lingyong Yan, Zixuan Yang, Erhan Zhang, Jiashu Zhao, Shuaiqiang Wang, Dawei Yin, Jiaxin Mao
Published: 2026-01-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.04703v1

Agentic search has emerged as a promising paradigm for complex information seeking by enabling Large Language Models (LLMs) to interleave reasoning with tool use. However, prevailing systems rely on monolithic agents that suffer from structural bottlenecks, including unconstrained reasoning outputs that inflate trajectories, sparse outcome-level rewards that complicate credit assignment, and stochastic search noise that destabilizes learning. To address these challenges, we propose \textbf{M-ASK} (Multi-Agent Search and Knowledge), a framework that explicitly decouples agentic search into two complementary roles: Search Behavior Agents, which plan and execute search actions, and Knowledge Management Agents, which aggregate, filter, and maintain a compact internal context. This decomposition allows each agent to focus on a well-defined subtask and reduces interference between search and context construction. Furthermore, to enable stable coordination, M-ASK employs turn-level rewards to provide granular supervision for both search decisions and knowledge updates. Experiments on multi-hop QA benchmarks demonstrate that M-ASK outperforms strong baselines, achieving not only superior answer accuracy but also significantly more stable training dynamics.\footnote{The source code for M-ASK is available at https://github.com/chenyiqun/M-ASK.}

---

### PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards

Authors: Mukesh Ghimire, Aosong Feng, Liwen You, Youzhi Luo, Fang Liu, Xuan Zhu
Published: 2026-01-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.04700v2

Current techniques for post-training Large Language Models (LLMs) rely either on costly human supervision or on external verifiers to boost performance on tasks such as mathematical reasoning and code generation. However, as LLMs improve their problem-solving, any further improvement will potentially require high-quality solutions to difficult problems that are not available to humans. As a result, learning from unlabeled data is becoming increasingly attractive in the research community. Existing methods extract learning signal from a model's consistency, either by majority voting or by converting the model's internal confidence into reward. Although internal consistency metric such as entropy or self-certainty require no human intervention, as we show in this work, these are unreliable signals for large-scale and long-term training. To address the unreliability, we propose PRISM, a unified training framework that uses a Process Reward Model (PRM) to guide learning alongside model's internal confidence in the absence of ground-truth labels. We show that effectively combining PRM with self-certainty can lead to both stable training and better test-time performance, and also keep the model's internal confidence in check. Code available at https://github.com/ghimiremukesh/PRISM.

---

### SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning

Authors: Zebin Han, Xudong Wang, Baichen Liu, Qi Lyu, Zhenduo Shang, Jiahua Dong, Lianqing Liu, Zhi Han
Published: 2026-01-08
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.04699v1

Sequential-Horizon Vision-and-Language Navigation (SH-VLN) presents a challenging scenario where agents should sequentially execute multi-task navigation guided by complex, long-horizon language instructions. Current vision-and-language navigation models exhibit significant performance degradation with such multi-task instructions, as information overload impairs the agent's ability to attend to observationally relevant details. To address this problem, we propose SeqWalker, a navigation model built on a hierarchical planning framework. Our SeqWalker features: i) A High-Level Planner that dynamically selects global instructions into contextually relevant sub-instructions based on the agent's current visual observations, thus reducing cognitive load; ii) A Low-Level Planner incorporating an Exploration-Verification strategy that leverages the inherent logical structure of instructions for trajectory error correction. To evaluate SH-VLN performance, we also extend the IVLN dataset and establish a new benchmark. Extensive experiments are performed to demonstrate the superiority of the proposed SeqWalker.

---

### TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning

Authors: Yinuo Wang, Mining Tan, Wenxiang Jiao, Xiaoxi Li, Hao Wang, Xuanyu Zhang, Yuan Lu, Weiming Dong
Published: 2026-01-08
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.04698v1

Travel planning is a sophisticated decision-making process that requires synthesizing multifaceted information to construct itineraries. However, existing travel planning approaches face several challenges: (1) Pruning candidate points of interest (POIs) while maintaining a high recall rate; (2) A single reasoning path restricts the exploration capability within the feasible solution space for travel planning; (3) Simultaneously optimizing hard constraints and soft constraints remains a significant difficulty. To address these challenges, we propose TourPlanner, a comprehensive framework featuring multi-path reasoning and constraint-gated reinforcement learning. Specifically, we first introduce a Personalized Recall and Spatial Optimization (PReSO) workflow to construct spatially-aware candidate POIs' set. Subsequently, we propose Competitive consensus Chain-of-Thought (CCoT), a multi-path reasoning paradigm that improves the ability of exploring the feasible solution space. To further refine the plan, we integrate a sigmoid-based gating mechanism into the reinforcement learning stage, which dynamically prioritizes soft-constraint satisfaction only after hard constraints are met. Experimental results on travel planning benchmarks demonstrate that TourPlanner achieves state-of-the-art performance, significantly surpassing existing methods in both feasibility and user-preference alignment.

---

### A Method for Constructing a Digital Transformation Driving Mechanism Based on Semantic Understanding of Large Models

Authors: Huayi Liu
Published: 2026-01-08
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.04696v1

In the process of digital transformation, enterprises are faced with problems such as insufficient semantic understanding of unstructured data and lack of intelligent decision-making basis in driving mechanisms. This study proposes a method that combines a large language model (LLM) and a knowledge graph. First, a fine-tuned BERT (Bidirectional Encoder Representations from Transformers) model is used to perform entity recognition and relationship extraction on multi-source heterogeneous texts, and GPT-4 is used to generate semantically enhanced vector representations; secondly, a two-layer graph neural network (GNN) architecture is designed to fuse the semantic vectors output by LLM with business metadata to construct a dynamic and scalable enterprise knowledge graph; then reinforcement learning is introduced to optimize decision path generation, and the reward function is used to drive the mechanism iteration. In the case of the manufacturing industry, this mechanism reduced the response time for equipment failure scenarios from 7.8 hours to 3.7 hours, the F1 value reached 94.3%, and the compensation for decision errors in the annual digital transformation cost decreased by 45.3%. This method significantly enhances the intelligence level and execution efficiency of the digital transformation driving mechanism by integrating large model semantic understanding with structured knowledge.

---

### Tape: A Cellular Automata Benchmark for Evaluating Rule-Shift Generalization in Reinforcement Learning

Authors: Enze Pan
Published: 2026-01-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.04695v2

Out-of-distribution generalization in reinforcement learning is hard to diagnose when benchmark shifts mix dynamics, observations, goals, and rewards. We address this with Tape, a controlled benchmark that isolates latent rule-shift in dynamics while keeping the observation-action interface fixed. The protocol combines deterministic splits, 20-seed replication, bootstrap uncertainty reporting, and continuous metrics for sparse-success regimes. Across baseline families, we find a consistent ID-to-OOD drop and strong heterogeneity across stable/periodic/chaotic rules. Importantly, this fragility appears even in an intentionally simple 1D deterministic setting, suggesting that many current RL algorithms remain brittle to latent-law changes under minimal confounds. To calibrate strict success, we report a protocol-matched true-dynamics random-shooting reference (p_oracle is almost 0.187) and oracle-normalized scores ON(p) = 100 p / p_oracle; this is a budgeted operational reference, not a global-optimality bound. A smaller feasibility regime (L = H = 16) with 100% rule-wise solvability helps separate reachability limits from policy failure. These results position Tape as a mechanism-oriented diagnostic for robust adaptation and latent-mechanism inference, and as a controlled benchmark relevant to broader AGI-oriented evaluation without making strong AGI sufficiency claims.

---

### ResMAS: Resilience Optimization in LLM-based Multi-agent Systems

Authors: Zhilun Zhou, Zihan Liu, Jiahe Liu, Qingyu Shao, Yihan Wang, Kun Shao, Depeng Jin, Fengli Xu
Published: 2026-01-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.04694v1

Large Language Model-based Multi-Agent Systems (LLM-based MAS), where multiple LLM agents collaborate to solve complex tasks, have shown impressive performance in many areas. However, MAS are typically distributed across different devices or environments, making them vulnerable to perturbations such as agent failures. While existing works have studied the adversarial attacks and corresponding defense strategies, they mainly focus on reactively detecting and mitigating attacks after they occur rather than proactively designing inherently resilient systems. In this work, we study the resilience of LLM-based MAS under perturbations and find that both the communication topology and prompt design significantly influence system resilience. Motivated by these findings, we propose ResMAS: a two-stage framework for enhancing MAS resilience. First, we train a reward model to predict the MAS's resilience, based on which we train a topology generator to automatically design resilient topology for specific tasks through reinforcement learning. Second, we introduce a topology-aware prompt optimization method that refines each agent's prompt based on its connections and interactions with other agents. Extensive experiments across a range of tasks show that our approach substantially improves MAS resilience under various constraints. Moreover, our framework demonstrates strong generalization ability to new tasks and models, highlighting its potential for building resilient MASs.

---

### Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding

Authors: Sungmok Jung, Yeonkyoung So, Joonhak Lee, Sangho Kim, Yelim Ahn, Jaejin Lee
Published: 2026-01-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.04693v2

Although negation is known to challenge large language models (LLMs), benchmarks for evaluating negation understanding-especially in Korean-are scarce. We conduct a corpus-based analysis of Korean negation and show that LLM performance degrades under negation. We then introduce Thunder-KoNUBench, a sentence-level negation understanding benchmark that reflects the empirical distribution of Korean negation phenomena. Evaluating 47 LLMs on Thunder-KoNUBench, we analyze the effects of model size and instruction tuning, and perform error analysis to better understand model behavior. We further show that fine-tuning on Thunder-KoNUBench improves negation understanding and broader contextual comprehension in Korean.

---

### PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderation

Authors: Naquee Rizwan, Subhankar Swain, Paramananda Bhaskar, Shehryaar Shah Khan, Gagan Aryan, Animesh Mukherjee
Published: 2026-01-08
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2601.04692v2

In this work, we examine hateful memes from three complementary angles - how to detect them, how to explain their content and how to intervene them before being posted - by applying a range of strategies built on top of generative AI models. To the best of our knowledge, explanation and intervention have typically been studied separately from detection, which does not reflect real-world conditions. Further, since curating large annotated datasets for meme moderation is prohibitively expensive, we propose a novel framework - PEST - that leverages task-specific generative VLMs and the few-shot adaptability of large VLMs to cater to different types of memes. We believe this is the first work focused on generalizable hateful meme moderation under limited data conditions, and has strong potential for deployment in real-world production scenarios. Warning: Contains potentially toxic contents.

---

### Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?

Authors: Mir Rayat Imtiaz Hossain, Leo Feng, Leonid Sigal, Mohamed Osama Ahmed
Published: 2026-01-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.04690v1

Large Language Models (LLMs) have emerged as promising recommendation systems, offering novel ways to model user preferences through generative approaches. However, many existing methods often rely solely on text semantics or incorporate collaborative signals in a limited manner, typically using only user or item embeddings. These methods struggle to handle multiple item embeddings representing user history, reverting to textual semantics and neglecting richer collaborative information. In this work, we propose a simple yet effective solution that projects user and item embeddings, learned from collaborative filtering, into the LLM token space via separate lightweight projector modules. A finetuned LLM then conditions on these projected embeddings alongside textual tokens to generate recommendations. Preliminary results show that this design effectively leverages structured user-item interaction data, improves recommendation performance over text-only LLM baselines, and offers a practical path for bridging traditional recommendation systems with modern LLMs.

---

### ToolGate: Contract-Grounded and Verified Tool Execution for LLMs

Authors: Yanming Liu, Xinyue Peng, Jiannan Cao, Xinyi Wang, Songhang Deng, Jintao Chen, Jianwei Yin, Xuhong Zhang
Published: 2026-01-08
Categories: cs.CL, cs.AI, cs.FL
arXiv: https://arxiv.org/abs/2601.04688v1

Large Language Models (LLMs) augmented with external tools have demonstrated remarkable capabilities in complex reasoning tasks. However, existing frameworks rely heavily on natural language reasoning to determine when tools can be invoked and whether their results should be committed, lacking formal guarantees for logical safety and verifiability. We present \textbf{ToolGate}, a forward execution framework that provides logical safety guarantees and verifiable state evolution for LLM tool calling. ToolGate maintains an explicit symbolic state space as a typed key-value mapping representing trusted world information throughout the reasoning process. Each tool is formalized as a Hoare-style contract consisting of a precondition and a postcondition, where the precondition gates tool invocation by checking whether the current state satisfies the required conditions, and the postcondition determines whether the tool's result can be committed to update the state through runtime verification. Our approach guarantees that the symbolic state evolves only through verified tool executions, preventing invalid or hallucinated results from corrupting the world representation. Experimental validation demonstrates that ToolGate significantly improves the reliability and verifiability of tool-augmented LLM systems while maintaining competitive performance on complex multi-step reasoning tasks. This work establishes a foundation for building more trustworthy and debuggable AI systems that integrate language models with external tools.

---

### WebCryptoAgent: Agentic Crypto Trading with Web Informatics

Authors: Ali Kurban, Wei Luo, Liangyu Zuo, Zeyu Zhang, Renda Han, Zhaolu Kang, Hao Tang, Yang Zhao
Published: 2026-01-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.04687v2

Cryptocurrency trading increasingly depends on timely integration of heterogeneous web information and market microstructure signals to support short-horizon decision making under extreme volatility. However, existing trading systems struggle to jointly reason over noisy multi-source web evidence while maintaining robustness to rapid price shocks at sub-second timescales. The first challenge lies in synthesizing unstructured web content, social sentiment, and structured OHLCV signals into coherent and interpretable trading decisions without amplifying spurious correlations, while the second challenge concerns risk control, as slow deliberative reasoning pipelines are ill-suited for handling abrupt market shocks that require immediate defensive responses. To address these challenges, we propose WebCryptoAgent, an agentic trading framework that decomposes web-informed decision making into modality-specific agents and consolidates their outputs into a unified evidence document for confidence-calibrated reasoning. We further introduce a decoupled control architecture that separates strategic hourly reasoning from a real-time second-level risk model, enabling fast shock detection and protective intervention independent of the trading loop. Extensive experiments on real-world cryptocurrency markets demonstrate that WebCryptoAgent improves trading stability, reduces spurious activity, and enhances tail-risk handling compared to existing baselines. Code will be available at https://github.com/AIGeeksGroup/WebCryptoAgent.

---

### Nightmare Dreamer: Dreaming About Unsafe States And Planning Ahead

Authors: Oluwatosin Oseni, Shengjie Wang, Jun Zhu, Micah Corah
Published: 2026-01-08
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2601.04686v1

Reinforcement Learning (RL) has shown remarkable success in real-world applications, particularly in robotics control. However, RL adoption remains limited due to insufficient safety guarantees. We introduce Nightmare Dreamer, a model-based Safe RL algorithm that addresses safety concerns by leveraging a learned world model to predict potential safety violations and plan actions accordingly. Nightmare Dreamer achieves nearly zero safety violations while maximizing rewards. Nightmare Dreamer outperforms model-free baselines on Safety Gymnasium tasks using only image observations, achieving nearly a 20x improvement in efficiency.

---

### HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution

Authors: Yang Zou, Xingyue Zhu, Kaiqi Han, Jun Ma, Xingyuan Li, Zhiying Jiang, Jinyuan Liu
Published: 2026-01-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.04682v1

Infrared video has been of great interest in visual tasks under challenging environments, but often suffers from severe atmospheric turbulence and compression degradation. Existing video super-resolution (VSR) methods either neglect the inherent modality gap between infrared and visible images or fail to restore turbulence-induced distortions. Directly cascading turbulence mitigation (TM) algorithms with VSR methods leads to error propagation and accumulation due to the decoupled modeling of degradation between turbulence and resolution. We introduce HATIR, a Heat-Aware Diffusion for Turbulent InfraRed Video Super-Resolution, which injects heat-aware deformation priors into the diffusion sampling path to jointly model the inverse process of turbulent degradation and structural detail loss. Specifically, HATIR constructs a Phasor-Guided Flow Estimator, rooted in the physical principle that thermally active regions exhibit consistent phasor responses over time, enabling reliable turbulence-aware flow to guide the reverse diffusion process. To ensure the fidelity of structural recovery under nonuniform distortions, a Turbulence-Aware Decoder is proposed to selectively suppress unstable temporal cues and enhance edge-aware feature aggregation via turbulence gating and structure-aware attention. We built FLIR-IVSR, the first dataset for turbulent infrared VSR, comprising paired LR-HR sequences from a FLIR T1050sc camera (1024 X 768) spanning 640 diverse scenes with varying camera and object motion conditions. This encourages future research in infrared VSR. Project page: https://github.com/JZ0606/HATIR

---

### DB-MSMUNet:Dual Branch Multi-scale Mamba UNet for Pancreatic CT Scans Segmentation

Authors: Qiu Guan, Zhiqiang Yang, Dezhang Ye, Yang Chen, Xinli Xu, Ying Tang
Published: 2026-01-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.04676v1

Accurate segmentation of the pancreas and its lesions in CT scans is crucial for the precise diagnosis and treatment of pancreatic cancer. However, it remains a highly challenging task due to several factors such as low tissue contrast with surrounding organs, blurry anatomical boundaries, irregular organ shapes, and the small size of lesions. To tackle these issues, we propose DB-MSMUNet (Dual-Branch Multi-scale Mamba UNet), a novel encoder-decoder architecture designed specifically for robust pancreatic segmentation. The encoder is constructed using a Multi-scale Mamba Module (MSMM), which combines deformable convolutions and multi-scale state space modeling to enhance both global context modeling and local deformation adaptation. The network employs a dual-decoder design: the edge decoder introduces an Edge Enhancement Path (EEP) to explicitly capture boundary cues and refine fuzzy contours, while the area decoder incorporates a Multi-layer Decoder (MLD) to preserve fine-grained details and accurately reconstruct small lesions by leveraging multi-scale deep semantic features. Furthermore, Auxiliary Deep Supervision (ADS) heads are added at multiple scales to both decoders, providing more accurate gradient feedback and further enhancing the discriminative capability of multi-scale features. We conduct extensive experiments on three datasets: the NIH Pancreas dataset, the MSD dataset, and a clinical pancreatic tumor dataset provided by collaborating hospitals. DB-MSMUNet achieves Dice Similarity Coefficients of 89.47%, 87.59%, and 89.02%, respectively, outperforming most existing state-of-the-art methods in terms of segmentation accuracy, edge preservation, and robustness across different datasets. These results demonstrate the effectiveness and generalizability of the proposed method for real-world pancreatic CT segmentation tasks.

---

### LLM-Guided Quantified SMT Solving over Uninterpreted Functions

Authors: Kunhang Lv, Yuhang Dong, Rui Han, Fuqi Jia, Feifei Ma, Jian Zhang
Published: 2026-01-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.04675v1

Quantified formulas with Uninterpreted Functions (UFs) over non-linear real arithmetic pose fundamental challenges for Satisfiability Modulo Theories (SMT) solving. Traditional quantifier instantiation methods struggle because they lack semantic understanding of UF constraints, forcing them to search through unbounded solution spaces with limited guidance. We present AquaForte, a framework that leverages Large Language Models to provide semantic guidance for UF instantiation by generating instantiated candidates for function definitions that satisfy the constraints, thereby significantly reducing the search space and complexity for solvers. Our approach preprocesses formulas through constraint separation, uses structured prompts to extract mathematical reasoning from LLMs, and integrates the results with traditional SMT algorithms through adaptive instantiation. AquaForte maintains soundness through systematic validation: LLM-guided instantiations yielding SAT solve the original problem, while UNSAT results generate exclusion clauses for iterative refinement. Completeness is preserved by fallback to traditional solvers augmented with learned constraints. Experimental evaluation on SMT-COMP benchmarks demonstrates that AquaForte solves numerous instances where state-of-the-art solvers like Z3 and CVC5 timeout, with particular effectiveness on satisfiable formulas. Our work shows that LLMs can provide valuable mathematical intuition for symbolic reasoning, establishing a new paradigm for SMT constraint solving.

---

### Estimating Causal Effects in Gaussian Linear SCMs with Finite Data

Authors: Aurghya Maiti, Prateek Jain
Published: 2026-01-08
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2601.04673v1

Estimating causal effects from observational data remains a fundamental challenge in causal inference, especially in the presence of latent confounders. This paper focuses on estimating causal effects in Gaussian Linear Structural Causal Models (GL-SCMs), which are widely used due to their analytical tractability. However, parameter estimation in GL-SCMs is often infeasible with finite data, primarily due to overparameterization. To address this, we introduce the class of Centralized Gaussian Linear SCMs (CGL-SCMs), a simplified yet expressive subclass where exogenous variables follow standardized distributions. We show that CGL-SCMs are equally expressive in terms of causal effect identifiability from observational distributions and present a novel EM-based estimation algorithm that can learn CGL-SCM parameters and estimate identifiable causal effects from finite observational samples. Our theoretical analysis is validated through experiments on synthetic data and benchmark causal graphs, demonstrating that the learned models accurately recover causal distributions.

---

### Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning

Authors: Wentao Zhang, Mingkun Xu, Qi Zhang, Shangyang Li, Derek F. Wong, Lifei Wang, Yanchao Yang, Lina Lu, Tao Fang
Published: 2026-01-08
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2601.04672v2

Agricultural disease diagnosis challenges VLMs, as conventional fine-tuning requires extensive labels, lacks interpretability, and generalizes poorly. While reasoning improves model robustness, existing methods rely on costly expert annotations and rarely address the open-ended, diverse nature of agricultural queries. To address these limitations, we propose \textbf{Agri-R1}, a reasoning-enhanced large model for agriculture. Our framework automates high-quality reasoning data generation via vision-language synthesis and LLM-based filtering, using only 19\% of available samples. Training employs Group Relative Policy Optimization (GRPO) with a novel reward function that integrates domain-specific lexicons and fuzzy matching to assess both correctness and linguistic flexibility in open-ended responses. Evaluated on CDDMBench, our resulting 3B-parameter model achieves performance competitive with 7B- to 13B-parameter baselines, showing a +27.9\% relative gain in disease recognition accuracy, +33.3\% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization over standard fine-tuning. These results suggest that automated reasoning synthesis paired with domain-aware reward design may provide a broadly applicable paradigm for RL-based VLM adaptation in data-scarce specialized domains. Our code and data are publicly available at: https://github.com/CPJ-Agricultural/Agri-R1.

---

### Learning Dynamics in RL Post-Training for Language Models

Authors: Akiyoshi Tomihari
Published: 2026-01-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.04670v1

Reinforcement learning (RL) post-training is a critical stage in modern language model development, playing a key role in improving alignment and reasoning ability. However, several phenomena remain poorly understood, including the reduction in output diversity. To gain a broader understanding of RL post-training, we analyze the learning dynamics of RL post-training from a perspective that has been studied in supervised learning but remains underexplored in RL. We adopt an empirical neural tangent kernel (NTK) framework and decompose the NTK into two components to characterize how RL updates propagate across training samples. Our analysis reveals that limited variability in feature representations can cause RL updates to systematically increase model confidence, providing an explanation for the commonly observed reduction in output diversity after RL post-training. Furthermore, we show that effective learning in this regime depends on rapidly shaping the classifier, which directly affects the gradient component of the NTK. Motivated by these insights, we propose classifier-first reinforcement learning (CF-RL), a simple two-stage training strategy that prioritizes classifier updates before standard RL optimization. Experimental results validate our theoretical analysis by demonstrating increased model confidence and accelerated optimization under CF-RL. Additional analysis shows that the mechanism underlying CF-RL differs from that of linear-probing-then-fine-tuning in supervised learning. Overall, our study formalizes the learning dynamics of RL post-training and motivates further analysis and improvement.

---

### Optimizing Path Planning using Deep Reinforcement Learning for UGVs in Precision Agriculture

Authors: Laukik Patade, Rohan Rane, Sandeep Pillai
Published: 2026-01-08
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.04668v1

This study focuses on optimizing path planning for unmanned ground vehicles (UGVs) in precision agriculture using deep reinforcement learning (DRL) techniques in continuous action spaces. The research begins with a review of traditional grid-based methods, such as A* and Dijkstra's algorithms, and discusses their limitations in dynamic agricultural environments, highlighting the need for adaptive learning strategies. The study then explores DRL approaches, including Deep Q-Networks (DQN), which demonstrate improved adaptability and performance in two-dimensional simulations. Enhancements such as Double Q-Networks and Dueling Networks are evaluated to further improve decision-making. Building on these results, the focus shifts to continuous action space models, specifically Deep Deterministic Policy Gradient (DDPG) and Twin Delayed Deep Deterministic Policy Gradient (TD3), which are tested in increasingly complex environments. Experiments conducted in a three-dimensional environment using ROS and Gazebo demonstrate the effectiveness of continuous DRL algorithms in navigating dynamic agricultural scenarios. Notably, the pretrained TD3 agent achieves a 95 percent success rate in dynamic environments, demonstrating the robustness of the proposed approach in handling moving obstacles while ensuring safety for both crops and the robot.

---

### Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning

Authors: Zhiyuan Chang, Mingyang Li, Yuekai Huang, Ziyou Jiang, Xiaojun Jia, Qian Xiong, Junjie Wang, Zhaoyang Li, Qing Wang
Published: 2026-01-08
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2601.04666v2

Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending against PI attacks faces two major issues: malicious instructions can be injected through diverse vectors, and injected instructions often lack clear semantic boundaries from the surrounding context, making them difficult to identify. To address these issues, we propose InstruCoT, a model enhancement method for PI defense that synthesizes diverse training data and employs instruction-level chain-of-thought fine-tuning, enabling LLMs to effectively identify and reject malicious instructions regardless of their source or position in the context. We evaluate InstruCoT across three critical dimensions: Behavior Deviation, Privacy Leakage, and Harmful Output. Experimental results across four LLMs demonstrate that InstruCoT significantly outperforms baselines in all dimensions while maintaining utility performance without degradation

---

### CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models

Authors: Yifan Le, Yunliang Li
Published: 2026-01-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.04664v2

Multilingual large language models (LLMs) achieve strong performance across languages, yet how language capabilities are organized at the neuron level remains poorly understood. Prior work has identified language-related neurons mainly through activation-based heuristics, which conflate language preference with functional importance. We propose CRANE, a relevance-based analysis framework that redefines language specificity in terms of functional necessity, identifying language-specific neurons through targeted neuron-level interventions. CRANE characterizes neuron specialization by their contribution to language-conditioned predictions rather than activation magnitude. Our implementation will be made publicly available. Neuron-level interventions reveal a consistent asymmetric pattern: masking neurons relevant to a target language selectively degrades performance on that language while preserving performance on other languages to a substantial extent, indicating language-selective but non-exclusive neuron specializations. Experiments on English, Chinese, and Vietnamese across multiple benchmarks, together with a dedicated relevance-based metric and base-to-chat model transfer analysis, show that CRANE isolates language-specific components more precisely than activation-based methods.

---

### LAMB: LLM-based Audio Captioning with Modality Gap Bridging via Cauchy-Schwarz Divergence

Authors: Hyeongkeun Lee, Jongmin Choi, KiHyun Nam, Joon Son Chung
Published: 2026-01-08
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.04658v2

Automated Audio Captioning aims to describe the semantic content of input audio. Recent works have employed large language models (LLMs) as a text decoder to leverage their reasoning capabilities. However, prior approaches that project audio features into the LLM embedding space without considering cross-modal alignment fail to fully utilize these capabilities. To address this, we propose LAMB, an LLM-based audio captioning framework that bridges the modality gap between audio embeddings and the LLM text embedding space. LAMB incorporates a Cross-Modal Aligner that minimizes Cauchy-Schwarz divergence while maximizing mutual information, yielding tighter alignment between audio and text at both global and token levels. We further design a Two-Stream Adapter that extracts semantically enriched audio embeddings, thereby delivering richer information to the Cross-Modal Aligner. Finally, leveraging the aligned audio embeddings, a proposed Token Guide directly computes scores within the LLM text embedding space to steer the output logits of generated captions. Experimental results confirm that our framework strengthens the reasoning capabilities of the LLM decoder, achieving state-of-the-art performance on AudioCaps.

---

### LLMs-Integrated Automatic Hate Speech Recognition Using Controllable Text Generation Models

Authors: Ryutaro Oshima, Yuya Hosoda, Youji Iiguni
Published: 2026-01-08
Categories: eess.AS, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2601.04654v1

This paper proposes an automatic speech recognition (ASR) model for hate speech using large language models (LLMs). The proposed method integrates the encoder of the ASR model with the decoder of the LLMs, enabling simultaneous transcription and censorship tasks to prevent the exposure of harmful content. Instruction tuning of the LLM to mask hate-related words with specific tokens requires an annotated hate speech dataset, which is limited. We generate text samples using an LLM with the Chain-of-Thought (CoT) prompting technique guided by cultural context and examples and then convert them into speech samples using a text-to-speech (TTS) system. However, some of them contain non-hate speech samples with hate-related words, which degrades the censorship performance. This paper filters the samples which text classification models correctly label as hate content. By adjusting the threshold for the number of correct answer models, we can control the level of hate in the generated dataset, allowing us to train the LLMs through curriculum learning in a gradual manner. Experimental results show that the proposed method achieves a masking accuracy of 58.6\% for hate-related words, surpassing previous baselines. We also confirm that the curriculum training contributes to the efficiency of both transcription and censorship tasks.

---

### Vibe Coding an LLM-powered Theorem Prover

Authors: Zhe Hou
Published: 2026-01-08
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2601.04653v1

We present Isabellm, an LLM-powered theorem prover for Isabelle/HOL that performs fully automatic proof synthesis. Isabellm works with any local LLM on Ollama and APIs such as Gemini CLI, and it is designed to run on consumer grade computers. The system combines a stepwise prover, which uses large language models to propose proof commands validated by Isabelle in a bounded search loop, with a higher-level proof planner that generates structured Isar outlines and attempts to fill and repair remaining gaps. The framework includes beam search for tactics, tactics reranker ML and RL models, premise selection with small transformer models, micro-RAG for Isar proofs built from AFP, and counter-example guided proof repair. All the code is implemented by GPT 4.1 - 5.2, Gemini 3 Pro, and Claude 4.5. Empirically, Isabellm can prove certain lemmas that defeat Isabelle's standard automation, including Sledgehammer, demonstrating the practical value of LLM-guided proof search. At the same time, we find that even state-of-the-art LLMs, such as GPT 5.2 Extended Thinking and Gemini 3 Pro struggle to reliably implement the intended fill-and-repair mechanisms with complex algorithmic designs, highlighting fundamental challenges in LLM code generation and reasoning. The code of Isabellm is available at https://github.com/zhehou/llm-isabelle

---

### Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models

Authors: Can Xu, Lingyong Yan, Jiayi Wu, Haosen Wang, Shuaiqiang Wang, Yuchen Li, Jizhou Huang, Dawei Yin, Xiang Li
Published: 2026-01-08
Categories: cs.AI, cs.IR, cs.MA
arXiv: https://arxiv.org/abs/2601.04651v2

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged perspective, limiting their ability to conduct deep, self-correcting reasoning over external documents, and (2) existing training paradigms rely excessively on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process. To address these issues, we propose an Reasoner-Verifier framework named Adversarial Reasoning RAG (ARR). The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage that requires no external scoring model. This reward combines explicit observational signals with internal model uncertainty to jointly optimize reasoning fidelity and verification rigor. Experiments on multiple benchmarks demonstrate the effectiveness of our method.

---

### Mechanism Design for Federated Learning with Non-Monotonic Network Effects

Authors: Xiang Li, Bing Luo, Jianwei Huang, Yuan Luo
Published: 2026-01-08
Categories: cs.GT, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2601.04648v1

Mechanism design is pivotal to federated learning (FL) for maximizing social welfare by coordinating self-interested clients. Existing mechanisms, however, often overlook the network effects of client participation and the diverse model performance requirements (i.e., generalization error) across applications, leading to suboptimal incentives and social welfare, or even inapplicability in real deployments. To address this gap, we explore incentive mechanism design for FL with network effects and application-specific requirements of model performance. We develop a theoretical model to quantify the impact of network effects on heterogeneous client participation, revealing the non-monotonic nature of such effects. Based on these insights, we propose a Model Trading and Sharing (MoTS) framework, which enables clients to obtain FL models through either participation or purchase. To further address clients' strategic behaviors, we design a Social Welfare maximization with Application-aware and Network effects (SWAN) mechanism, exploiting model customer payments for incentivization. Experimental results on a hardware prototype demonstrate that our SWAN mechanism outperforms existing FL mechanisms, improving social welfare by up to $352.42\%$ and reducing extra incentive costs by $93.07\%$.

---

### Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search

Authors: Prateek Jain, Shabari S Nair, Ritesh Goru, Prakhar Agarwal, Ajay Yadav, Yoga Sri Varshan Varadharajan, Constantine Caramanis
Published: 2026-01-08
Categories: cs.IR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.04646v4

Large-scale multi-tenant retrieval systems generate extensive query logs but lack curated relevance labels for effective domain adaptation, resulting in substantial underutilized "dark data." This challenge is compounded by the high cost of model updates, as jointly fine-tuning query and document encoders requires full corpus re-indexing, which is impractical in multi-tenant settings with thousands of isolated indices. We introduce DevRev-Search, a passage retrieval benchmark for technical customer support built via a fully automated pipeline. Candidate generation uses fusion across diverse sparse and dense retrievers, followed by an LLM-as-a-Judge for consistency filtering and relevance labeling. We further study and systematically evaluate index-preserving query-only adaptation strategies that fine-tune only the query-encoder while keeping the document indices fixed. Experiments on DevRev-Search, SciFact, and FiQA-2018 show that parameter-efficient fine-tuning of the query encoder delivers a remarkable quality-efficiency trade-off, enabling scalable and practical enterprise multi-tenant retrieval.

---

### DP-MGTD: Privacy-Preserving Machine-Generated Text Detection via Adaptive Differentially Private Entity Sanitization

Authors: Lionel Z. Wang, Yusheng Zhao, Jiabin Luo, Xinfeng Li, Lixu Wang, Yinan Peng, Haoyang Li, XiaoFeng Wang, Wei Dong
Published: 2026-01-08
Categories: cs.CR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.04641v2

The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict between authorship verification and privacy preservation. Standard anonymization techniques often disrupt linguistic fluency, while rigorous Differential Privacy (DP) mechanisms typically degrade the statistical signals required for accurate detection. To resolve this dilemma, we propose \textbf{DP-MGTD}, a framework incorporating an Adaptive Differentially Private Entity Sanitization algorithm. Our approach utilizes a two-stage mechanism that performs noisy frequency estimation and dynamically calibrates privacy budgets, applying Laplace and Exponential mechanisms to numerical and textual entities respectively. Crucially, we identify a counter-intuitive phenomenon where the application of DP noise amplifies the distinguishability between human and machine text by exposing distinct sensitivity patterns to perturbation. Extensive experiments on the MGTBench-2.0 dataset show that our method achieves near-perfect detection accuracy, significantly outperforming non-private baselines while satisfying strict privacy guarantees.

---

### SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation

Authors: Sirry Chen, Jieyi Wang, Wei Chen, Zhongyu Wei
Published: 2026-01-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.04638v2

Medical consultations are intrinsically speech-centric. However, most prior works focus on long-text-based interactions, which are cumbersome and patient-unfriendly. Recent advances in speech language models (SpeechLMs) have enabled more natural speech-based interaction, yet the scarcity of medical speech data and the inefficiency of directly fine-tuning on speech data jointly hinder the adoption of SpeechLMs in medical consultation. In this paper, we propose SpeechMedAssist, a SpeechLM natively capable of conducting speech-based multi-turn interactions with patients. By exploiting the architectural properties of SpeechLMs, we decouple the conventional one-stage training into a two-stage paradigm consisting of (1) Knowledge & Capability Injection via Text and (2) Modality Re-alignment with Limited Speech Data, thereby reducing the requirement for medical speech data to only 10k synthesized samples. To evaluate SpeechLMs for medical consultation scenarios, we design a benchmark comprising both single-turn question answering and multi-turn simulated interactions. Experimental results show that our model outperforms all baselines in both effectiveness and robustness in most evaluation settings.

---

### MAGA-Bench: Machine-Augment-Generated Text via Alignment Detection Benchmark

Authors: Anyang Song, Ying Cheng, Yiqian Xu, Rui Feng
Published: 2026-01-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.04633v2

Machine-Generated Text (MGT) is becoming increasingly difficult to distinguish from Human-Written Text (HWT). This trend has exacerbated malicious activities such as fake news and online fraud. The generalization ability of fine-tuned detectors relies heavily on dataset quality, and simply expanding the sources of MGT may become increasingly insufficient. Further augmentation of the generation process is required. Based on HC-Var's theory, enhancing the human-like alignment of MGT not only facilitates robustness testing of existing detectors but also boosts the generalization ability of detectors fine-tuned on such aligned MGT datasets. Therefore, we propose the \textbf{M}achine-\textbf{A}ugment-\textbf{G}enerated Text via \textbf{A}lignment (MAGA) Detection Benchmark. MAGA integrates several alignment methods, ranging from prompt construction to \textbf{G}enerator-\textbf{D}etector \textbf{A}dversarial \textbf{R}einforcement \textbf{L}earning (GDARL) and the reasoning process. In our experiments, the RoBERTa detector fine-tuned on MAGA achieves an average improvement of 4.60\% in generalization AUC. Conversely, the aligned MGTs in MAGA also lead to an average decrease of 8.13\% in the AUC of selected detectors. We hope the MAGA Benchmark will provide valuable insights for future research on the generalization ability of MGT detectors.

---

### From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset

Authors: Haneul Yoo, Won Ik Cho, Geunhye Kim, Jiyoon Han
Published: 2026-01-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.04632v2

Large language models (LLMs) achieve strong performance on many tasks, but their progress remains uneven across languages and cultures, often reflecting values latent in English-centric training data. To enable practical cultural alignment, we propose a scalable approach that leverages national social studies curricula as a foundation for culture-aware supervision. We introduce CuCu, an automated multi-agent LLM framework that transforms national textbook curricula into open-ended, culture-specific question-answer pairs for supervised fine-tuning (SFT). Applying CuCu to the Korean national social studies curriculum, we construct KCaQA, comprising 34.1k open-ended QA pairs. Our analyses and training experiments suggest that KCaQA covers culture-specific topics and produces responses grounded in local sociocultural contexts.

---

### Beyond the "Truth": Investigating Election Rumors on Truth Social During the 2024 Election

Authors: Etienne Casanova, R. Michael Alvarez
Published: 2026-01-08
Categories: cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2601.04631v1

Large language models (LLMs) offer unprecedented opportunities for analyzing social phenomena at scale. This paper demonstrates the value of LLMs in psychological measurement by (1) compiling the first large-scale dataset of election rumors on a niche alt-tech platform, (2) developing a multistage Rumor Detection Agent that leverages LLMs for high-precision content classification, and (3) quantifying the psychological dynamics of rumor propagation, specifically the "illusory truth effect" in a naturalistic setting. The Rumor Detection Agent combines (i) a synthetic data-augmented, fine-tuned RoBERTa classifier, (ii) precision keyword filtering, and (iii) a two-pass LLM verification pipeline using GPT-4o mini. The findings reveal that sharing probability rises steadily with each additional exposure, providing large-scale empirical evidence for dose-response belief reinforcement in ideologically homogeneous networks. Simulation results further demonstrate rapid contagion effects: nearly one quarter of users become "infected" within just four propagation iterations. Taken together, these results illustrate how LLMs can transform psychological science by enabling the rigorous measurement of belief dynamics and misinformation spread in massive, real-world datasets.

---

### AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering

Authors: Di Zhang
Published: 2026-01-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.04620v1

Recent progress in large language model (LLM) agents has largely focused on embedding self-improvement mechanisms inside the agent or searching over many concurrent variants. While these approaches can raise aggregate scores, they often yield unstable and hard-to-audit improvement trajectories, making it difficult to guarantee non-regression or to reason about failures across versions. We reframe agent improvement as \textbf{release engineering}: agents are treated as shippable artifacts, and improvement is externalized into a regression-aware release pipeline. We introduce \textbf{AgentDevel}, a release engineering pipeline that iteratively runs the current agent, produces implementation-blind, symptom-level quality signals from execution traces, synthesizes a single release candidate (RC) via executable diagnosis, and promotes it under flip-centered gating. AgentDevel features three core designs: (i) an implementation-blind LLM critic that characterizes failure appearances without accessing agent internals, (ii) script-based executable diagnosis that aggregates dominant symptom patterns and produces auditable engineering specifications, and (iii) flip-centered gating that prioritizes pass to fail regressions and fail to pass fixes as first-class evidence. Unlike population-based search or in-agent self-refinement, AgentDevel maintains a single canonical version line and emphasizes non-regression as a primary objective. Experiments on execution-heavy benchmarks demonstrate that AgentDevel yields stable improvements with significantly fewer regressions while producing reproducible, auditable artifacts. Overall, AgentDevel provides a practical development discipline for building, debugging, and releasing LLM agents as software development.

---

### DeepHalo: A Neural Choice Model with Controllable Context Effects

Authors: Shuhan Zhang, Zhi Wang, Rui Gao, Shuang Li
Published: 2026-01-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.04616v1

Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows that preferences are often influenced by the composition of the choice set itself -- a phenomenon known as the context effect or Halo effect. These effects can manifest as pairwise (first-order) or even higher-order interactions among the available alternatives. Recent models that attempt to capture such effects either focus on the featureless setting or, in the feature-based setting, rely on restrictive interaction structures or entangle interactions across all orders, which limits interpretability. In this work, we propose DeepHalo, a neural modeling framework that incorporates features while enabling explicit control over interaction order and principled interpretation of context effects. Our model enables systematic identification of interaction effects by order and serves as a universal approximator of context-dependent choice functions when specialized to a featureless setting. Experiments on synthetic and real-world datasets demonstrate strong predictive performance while providing greater transparency into the drivers of choice.

---

### HyperAlign: Hyperbolic Entailment Cones for Adaptive Text-to-Image Alignment Assessment

Authors: Wenzhi Chen, Bo Hu, Leida Li, Lihuo He, Wen Lu, Xinbo Gao
Published: 2026-01-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.04614v2

With the rapid development of text-to-image generation technology, accurately assessing the alignment between generated images and text prompts has become a critical challenge. Existing methods rely on Euclidean space metrics, neglecting the structured nature of semantic alignment, while lacking adaptive capabilities for different samples. To address these limitations, we propose HyperAlign, an adaptive text-to-image alignment assessment framework based on hyperbolic entailment geometry. First, we extract Euclidean features using CLIP and map them to hyperbolic space. Second, we design a dynamic-supervision entailment modeling mechanism that transforms discrete entailment logic into continuous geometric structure supervision. Finally, we propose an adaptive modulation regressor that utilizes hyperbolic geometric features to generate sample-level modulation parameters, adaptively calibrating Euclidean cosine similarity to predict the final score. HyperAlign achieves highly competitive performance on both single database evaluation and cross-database generalization tasks, fully validating the effectiveness of hyperbolic geometric modeling for image-text alignment assessment.

---

### Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR

Authors: Yihong Tang, Kehai Chen, Xuefeng Bai, Benyou Wang, Zeming Liu, Haifeng Wang, Min Zhang
Published: 2026-01-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.04611v1

Current role-playing agents (RPAs) are typically constructed by imitating surface-level behaviors, but this approach lacks internal cognitive consistency, often causing out-of-character errors in complex situations. To address this, we propose Character-R1, a framework designed to provide comprehensive verifiable reward signals for effective role-aware reasoning, which are missing in recent studies. Specifically, our framework comprises three core designs: (1) Cognitive Focus Reward, which enforces explicit label-based analysis of 10 character elements (e.g., worldview) to structure internal cognition; (2) Reference-Guided Reward, which utilizes overlap-based metrics with reference responses as optimization anchors to enhance exploration and performance; and (3) Character-Conditioned Reward Normalization, which adjusts reward distributions based on character categories to ensure robust optimization across heterogeneous roles. Extensive experiments demonstrate that Character-R1 significantly outperforms existing methods in knowledge, memory and others.

---

### Evaluating Human and Machine Confidence in Phishing Email Detection: A Comparative Study

Authors: Paras Jain, Khushi Dhar, Olyemi E. Amujo, Esa M. Rantanen
Published: 2026-01-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.04610v1

Identifying deceptive content like phishing emails demands sophisticated cognitive processes that combine pattern recognition, confidence assessment, and contextual analysis. This research examines how human cognition and machine learning models work together to distinguish phishing emails from legitimate ones. We employed three interpretable algorithms Logistic Regression, Decision Trees, and Random Forests training them on both TF-IDF features and semantic embeddings, then compared their predictions against human evaluations that captured confidence ratings and linguistic observations. Our results show that machine learning models provide good accuracy rates, but their confidence levels vary significantly. Human evaluators, on the other hand, use a greater variety of language signs and retain more consistent confidence. We also found that while language proficiency has minimal effect on detection performance, aging does. These findings offer helpful direction for creating transparent AI systems that complement human cognitive functions, ultimately improving human-AI cooperation in challenging content analysis tasks.

---

### When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation

Authors: Rhea Kapur, Robert Hawkins, Elisa Kreiss
Published: 2026-01-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.04609v2

Vision-language models (VLMs) are increasingly used to make visual content accessible via text-based descriptions. In current systems, however, description specificity is often conflated with their length. We argue that these two concepts must be disentangled: descriptions can be concise yet dense with information, or lengthy yet vacuous. We define specificity relative to a contrast set, where a description is more specific to the extent that it picks out the target image better than other possible images. We construct a dataset that controls for length while varying information content, and validate that people reliably prefer more specific descriptions regardless of length. We find that controlling for length alone cannot account for differences in specificity: how the length budget is allocated makes a difference. These results support evaluation approaches that directly prioritize specificity over verbosity.

---

### Distributionally Robust Recovery of Omitted Factors from Forecast Residuals with Application to Interest Rate Risk Management

Authors: Jinjun Liu, Ming-Yen Cheng
Published: 2026-01-08
Categories: q-fin.MF, q-fin.CP, stat.ML
arXiv: https://arxiv.org/abs/2601.04608v3

A forecasting model compresses its predictors into an estimate of a conditional mean, and the systematic structure that estimate omits survives in the second moment of its forecast errors. Accuracy comparisons do not measure this structure, and variance-based extraction does not recover the part of it that a given decision bears. In this paper, we propose a distributionally robust framework that recovers the omitted structure from the residuals of a fixed forecaster: a decision is made robust over a two-layer moment ambiguity set on the standardized residual cross-section, and the discovery statistic is the covariance forcing, the component of the decision's residual risk transverse to its exposure. We demonstrate that the forcing is invariant to shrinkage and to isotropic inflation of the covariance, so the recovered direction is a property of the residuals rather than of the regularization, the sense in which the recovery is ground truth. This is confirmed on monthly U.S. Treasury zero-coupon yields from 2006 to 2025, where the recovered factor is named by factor-adjusted robust selection against a panel of 111 macroeconomic, Treasury supply-and-demand, and financial indicators. From the residuals of the linear factor-augmented dynamic Nelson-Siegel benchmark the factor names as a leading business-cycle factor, anchored on the Conference Board leading index and certified by a block-permutation test; from those of the more accurate nonlinear random forest benchmark the same procedure selects the same real-activity family without certification. A neutralization test completes the evidence: removing the recovered factor from the deployed duration position leaves volatility essentially unchanged and worsens the tail, so the factor is a material systematic risk the position bears.

---

### HUR-MACL: High-Uncertainty Region-Guided Multi-Architecture Collaborative Learning for Head and Neck Multi-Organ Segmentation

Authors: Xiaoyu Liu, Siwen Wei, Linhao Qu, Mingyuan Pan, Chengsheng Zhang, Yonghong Shi, Zhijian Song
Published: 2026-01-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.04607v1

Accurate segmentation of organs at risk in the head and neck is essential for radiation therapy, yet deep learning models often fail on small, complexly shaped organs. While hybrid architectures that combine different models show promise, they typically just concatenate features without exploiting the unique strengths of each component. This results in functional overlap and limited segmentation accuracy. To address these issues, we propose a high uncertainty region-guided multi-architecture collaborative learning (HUR-MACL) model for multi-organ segmentation in the head and neck. This model adaptively identifies high uncertainty regions using a convolutional neural network, and for these regions, Vision Mamba as well as Deformable CNN are utilized to jointly improve their segmentation accuracy. Additionally, a heterogeneous feature distillation loss was proposed to promote collaborative learning between the two architectures in high uncertainty regions to further enhance performance. Our method achieves SOTA results on two public datasets and one private dataset.

---

### Crystal Generation using the Fully Differentiable Pipeline and Latent Space Optimization

Authors: Osman Goni Ridwan, Gilles Frapper, Hongfei Xue, Qiang Zhu
Published: 2026-01-08
Categories: cond-mat.mtrl-sci, cs.AI, cs.LG, physics.atm-clus
arXiv: https://arxiv.org/abs/2601.04606v2

We present a materials generation framework that couples a symmetry-conditioned variational autoencoder (CVAE) with a differentiable SO(3) power spectrum objective to steer candidates toward a specified local environment under the crystallographic constraints. In particular, we implement a fully differentiable pipeline to enable batch-wise optimization on both direct and latent crystallographic representations. Using the GPU acceleration, this implementation achieves about fivefold speed compared to our previous CPU workflow, while yielding comparable outcomes. In addition, we introduce the optimization strategy that alternatively performs optimization on the direct and latent crystal representations. This dual-level relaxation approach can effectively escape local minima defined by different objective gradients, thus increasing the success rate of generating complex structures satisfying the target local environments. This framework can be extended to systems consisting of multi-components and multi-environments, providing a scalable route to generate material structures with the target local environment.

---

### Detection of Deployment Operational Deviations for Safety and Security of AI-Enabled Human-Centric Cyber Physical Systems

Authors: Bernard Ngabonziza, Ayan Banerjee, Sandeep K. S. Gupta
Published: 2026-01-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.04605v1

In recent years, Human-centric cyber-physical systems have increasingly involved artificial intelligence to enable knowledge extraction from sensor-collected data. Examples include medical monitoring and control systems, as well as autonomous cars. Such systems are intended to operate according to the protocols and guidelines for regular system operations. However, in many scenarios, such as closed-loop blood glucose control for Type 1 diabetics, self-driving cars, and monitoring systems for stroke diagnosis. The operations of such AI-enabled human-centric applications can expose them to cases for which their operational mode may be uncertain, for instance, resulting from the interactions with a human with the system. Such cases, in which the system is in uncertain conditions, can violate the system's safety and security requirements. This paper will discuss operational deviations that can lead these systems to operate in unknown conditions. We will then create a framework to evaluate different strategies for ensuring the safety and security of AI-enabled human-centric cyber-physical systems in operation deployment. Then, as an example, we show a personalized image-based novel technique for detecting the non-announcement of meals in closed-loop blood glucose control for Type 1 diabetics.

---

### Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks

Authors: Hoagy Cunningham, Jerry Wei, Zihan Wang, Andrew Persic, Alwin Peng, Jordan Abderrachid, Raj Agarwal, Bobby Chen, Austin Cohen, Andy Dau, Alek Dimitriev, Rob Gilson et al.
Published: 2026-01-08
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.04603v1

We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to previous-generation defenses. Our system combines several key insights. First, we develop exchange classifiers that evaluate model responses in their full conversational context, which addresses vulnerabilities in last-generation systems that examine outputs in isolation. Second, we implement a two-stage classifier cascade where lightweight classifiers screen all traffic and escalate only suspicious exchanges to more expensive classifiers. Third, we train efficient linear probe classifiers and ensemble them with external classifiers to simultaneously improve robustness and reduce computational costs. Together, these techniques yield a production-grade system achieving a 40x computational cost reduction compared to our baseline exchange classifier, while maintaining a 0.05% refusal rate on production traffic. Through extensive red-teaming comprising over 1,700 hours, we demonstrate strong protection against universal jailbreaks -- no attack on this system successfully elicited responses to all eight target queries comparable in detail to an undefended model. Our work establishes Constitutional Classifiers as practical and efficient safeguards for large language models.

---

### On the Limitations of Rank-One Model Editing in Answering Multi-hop Questions

Authors: Zhiyuan He, Binghan Chen, Tianxiang Xiong, Ziyang Sun, Mozhao Zhu, Xi Chen
Published: 2026-01-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.04600v1

Recent advances in Knowledge Editing (KE), particularly Rank-One Model Editing (ROME), show superior efficiency over fine-tuning and in-context learning for updating single-hop facts in transformers. However, these methods face significant challenges when applied to multi-hop reasoning tasks requiring knowledge chaining. In this work, we study the effect of editing knowledge with ROME on different layer depths and identify three key failure modes. First, the "hopping-too-late" problem occurs as later layers lack access to necessary intermediate representations. Second, generalization ability deteriorates sharply when editing later layers. Third, the model overfits to edited knowledge, incorrectly prioritizing edited-hop answers regardless of context. To mitigate the issues of "hopping-too-late" and generalisation decay, we propose Redundant Editing, a simple yet effective strategy that enhances multi-hop reasoning. Our experiments demonstrate that this approach can improve accuracy on 2-hop questions by at least 15.5 percentage points, representing a 96% increase over the previous single-edit strategy, while trading off some specificity and language naturalness.

---

### THaLLE-ThaiLLM: Domain-Specialized Small LLMs for Finance and Thai -- Technical Report

Authors: KBTG Labs, :, Anuruth Lertpiya, Danupat Khamnuansin, Kantapong Sucharitpongpan, Pornchanan Balee, Tawunrat Chalothorn, Thadpong Pongthawornkamol, Monchai Lertsutthiwong
Published: 2026-01-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.04597v1

Large Language Models (LLMs) have demonstrated significant potential across various domains, particularly in banking and finance, where they can automate complex tasks and enhance decision-making at scale. Due to privacy, security, and regulatory concerns, organizations often prefer on-premise deployment of LLMs. The ThaiLLM initiative aims to enhance Thai language capabilities in open-LLMs, enabling Thai industry to leverage advanced language models. However, organizations often face a trade-off between deploying multiple specialized models versus the prohibitive expense of training a single multi-capability model. To address this, we explore model merging as a resource-efficient alternative for developing high-performance, multi-capability LLMs. We present results from two key experiments: first, merging Qwen-8B with ThaiLLM-8B demonstrates how ThaiLLM-8B enhances Thai general capabilities, showing an uplift of M3 and M6 O-NET exams over the general instruction-following Qwen-8B. Second, we merge Qwen-8B with both ThaiLLM-8B and THaLLE-CFA-8B. This combination results in further improvements in performance across both general and financial domains, by demonstrating an uplift in both M3 and M6 O-NET, Flare-CFA, and Thai-IC benchmarks. The report showcases the viability of model merging for efficiently creating multi-capability LLMs.

---

### Density Matrix RNN (DM-RNN): A Quantum Information Theoretic Framework for Modeling Musical Context and Polyphony

Authors: Joonwon Seo, Mariana Montiel
Published: 2026-01-08
Categories: cs.LG, cs.SD, math-ph
arXiv: https://arxiv.org/abs/2601.04592v1

Classical Recurrent Neural Networks (RNNs) summarize musical context into a deterministic hidden state vector, imposing an information bottleneck that fails to capture the inherent ambiguity in music. We propose the Density Matrix RNN (DM-RNN), a novel theoretical architecture utilizing the Density Matrix. This allows the model to maintain a statistical ensemble of musical interpretations (a mixed state), capturing both classical probabilities and quantum coherences. We rigorously define the temporal dynamics using Quantum Channels (CPTP maps). Crucially, we detail a parameterization strategy based on the Choi-Jamiolkowski isomorphism, ensuring the learned dynamics remain physically valid (CPTP) by construction. We introduce an analytical framework using Von Neumann Entropy to quantify musical uncertainty and Quantum Mutual Information (QMI) to measure entanglement between voices. The DM-RNN provides a mathematically rigorous framework for modeling complex, ambiguous musical structures.

---

### MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing

Authors: Zihao Lin, Wanrong Zhu, Jiuxiang Gu, Jihyung Kil, Christopher Tensmeyer, Lin Zhang, Shilong Liu, Ruiyi Zhang, Lifu Huang, Vlad I. Morariu, Tong Sun
Published: 2026-01-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.04589v2

Real-world design documents (e.g., posters) are inherently multi-layered, combining decoration, text, and images. Editing them from natural-language instructions requires fine-grained, layer-aware reasoning to identify relevant layers and coordinate modifications. Prior work largely overlooks multi-layer design document editing, focusing instead on single-layer image editing or multi-layer generation, which assume a flat canvas and lack the reasoning needed to determine what and where to modify. To address this gap, we introduce the Multi-Layer Document Editing Agent (MiLDEAgent), a reasoning-based framework that combines an RL-trained multimodal reasoner for layer-wise understanding with an image editor for targeted modifications. To systematically benchmark this setting, we introduce the MiLDEBench, a human-in-the-loop corpus of over 20K design documents paired with diverse editing instructions. The benchmark is complemented by a task-specific evaluation protocol, MiLDEEval, which spans four dimensions including instruction following, layout consistency, aesthetics, and text rendering. Extensive experiments on 14 open-source and 2 closed-source models reveal that existing approaches fail to generalize: open-source models often cannot complete multi-layer document editing tasks, while closed-source models suffer from format violations. In contrast, MiLDEAgent achieves strong layer-aware reasoning and precise editing, significantly outperforming all open-source baselines and attaining performance comparable to closed-source models, thereby establishing the first strong baseline for multi-layer document editing.

---