TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making

Using effective generalization capabilities of vision language models (VLMs) in context-specific dynamic tasks for embodied artificial intelligence remains a significant challenge. Although supervised fine-tuned models can better align with the real physical world, they still exhibit sluggish responses and hallucination issues in dynamically changing environments, necessitating further alignment. Existing post-SFT methods, reliant on reinforcement learning and chain-of-thought (CoT) approaches, are constrained by sparse rewards and action-only optimization, resulting in low sample efficiency, poor consistency, and model degradation. To address these issues, this paper proposes Thought-Centric Preference Optimization (TCPO) for effective embodied decision-making. Specifically, TCPO introduces a stepwise preference-based optimization approach, transforming sparse reward signals into richer step sample pairs. It emphasizes the alignment of the model's intermediate reasoning process, mitigating the problem of model degradation. Moreover, by incorporating Action Policy Consistency Constraint (APC), it further imposes consistency constraints on the model output. Experiments in the ALFWorld environment demonstrate an average success rate of 26.67%, achieving a 6% improvement over RL4VLM and validating the effectiveness of our approach in mitigating model degradation after fine-tuning. These results highlight the potential of integrating preference-based learning techniques with CoT processes to enhance the decision-making capabilities of vision-language models in embodied agents.

Stop Spinning Wheels: Mitigating LLM Overthinking via Mining Patterns for Early Reasoning Exit

Large language models (LLMs) enhance complex reasoning tasks by scaling the individual thinking process. However, prior work shows that overthinking can degrade overall performance. Motivated by observed patterns in thinking length and content length, we categorize reasoning into three stages: insufficient exploration stage, compensatory reasoning stage, and reasoning convergence stage. Typically, LLMs produce correct answers in the compensatory reasoning stage, whereas reasoning convergence often triggers overthinking, causing increased resource usage or even infinite loops. Therefore, mitigating overthinking hinges on detecting the end of the compensatory reasoning stage, defined as the Reasoning Completion Point (RCP). RCP typically appears at the end of the first complete reasoning cycle and can be identified by querying the LLM sentence by sentence or monitoring the probability of an end-of-thinking token (e.g., \texttt{</think>}), though these methods lack an efficient and precise balance. To improve this, we mine more sensitive and consistent RCP patterns and develop a lightweight thresholding strategy based on heuristic rules. Experimental evaluations on benchmarks (AIME24, AIME25, GPQA-D) demonstrate that the proposed method reduces token consumption while preserving or enhancing reasoning accuracy.

Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models

Large language models (LLMs) have demonstrated exceptional performance in understanding and generating semantic patterns, making them promising candidates for sequential recommendation tasks. However, when combined with conventional recommendation models (CRMs), LLMs often face challenges related to high inference costs and static knowledge transfer methods. In this paper, we propose a novel mutual distillation framework, LLMD4Rec, that fosters dynamic and bidirectional knowledge exchange between LLM-centric and CRM-based recommendation systems. Unlike traditional unidirectional distillation methods, LLMD4Rec enables iterative optimization by alternately refining both models, enhancing the semantic understanding of CRMs and enriching LLMs with collaborative signals from user-item interactions. By leveraging sample-wise adaptive weighting and aligning output distributions, our approach eliminates the need for additional parameters while ensuring effective knowledge transfer. Extensive experiments on real-world datasets demonstrate that LLMD4Rec significantly improves recommendation accuracy across multiple benchmarks without increasing inference costs. This method provides a scalable and efficient solution for combining the strengths of both LLMs and CRMs in sequential recommendation systems.

UAV-Enabled Joint Sensing, Communication, Powering and Backhaul Transmission in Maritime Monitoring Networks

This paper addresses the challenge of energy-constrained maritime monitoring networks by proposing an unmanned aerial vehicle (UAV)-enabled integrated sensing, communication, powering and backhaul transmission scheme with a tailored time-division duplex frame structure. Within each time slot, the UAV sequentially implements sensing, wireless charging and uplink receiving with buoys, and lastly forwards part of collected data to the central ship via backhaul links. Considering the tight coupling among these functions, we jointly optimize time allocation, UAV trajectory, UAV-buoy association, and power scheduling to maximize the performance of data collection, with the practical consideration of sea clutter effects during UAV sensing. A novel optimization framework combining alternating optimization, quadratic transform and augmented first-order Taylor approximation is developed, which demonstrates good convergence behavior and robustness. Simulation results show that under sensing quality-of-service constraint, buoys are able to achieve an average data rate over 22bps/Hz using around 2mW harvested power per active time slot, validating the scheme's effectiveness for open-sea monitoring. Additionally, it is found that under the influence of sea clutters, the optimal UAV trajectory always keeps a certain distance with buoys to strike a balance between sensing and other multi-functional transmissions.

Dynamic Fisher-weighted Model Merging via Bayesian Optimization

The fine-tuning of pre-trained language models has resulted in the widespread availability of task-specific models. Model merging offers an efficient way to create multi-task models by combining these fine-tuned models at the parameter level, without the need for training data or joint training on multiple datasets. Existing merging approaches typically involve scaling the parameters model-wise or integrating parameter importance parameter-wise. Both approaches exhibit their own weaknesses, leading to a notable performance gap compared to multi-task fine-tuning. In this paper, we unify these seemingly distinct strategies into a more general merging framework, and introduce Dynamic Fisher-weighted Merging (DF-Merge). Specifically, candidate models are associated with a set of coefficients that linearly scale their fine-tuned parameters. Bayesian optimization is applied to dynamically adjust these coefficients, aiming to maximize overall performance on validation sets. Each iteration of this process integrates parameter importance based on the Fisher information conditioned by the coefficients. Experimental results show that DF-Merge outperforms strong baselines across models of different sizes and a variety of tasks. Our analysis shows that the effectiveness of DF-Merge arises from the unified view of merging and that near-optimal performance is achievable in a few iterations, even with minimal validation data.

FedCIA: Federated Collaborative Information Aggregation for Privacy-Preserving Recommendation

Recommendation algorithms rely on user historical interactions to deliver personalized suggestions, which raises significant privacy concerns. Federated recommendation algorithms tackle this issue by combining local model training with server-side model aggregation, where most existing algorithms use a uniform weighted summation to aggregate item embeddings from different client models. This approach has three major limitations: 1) information loss during aggregation, 2) failure to retain personalized local features, and 3) incompatibility with parameter-free recommendation algorithms. To address these limitations, we first review the development of recommendation algorithms and recognize that their core function is to share collaborative information, specifically the global relationship between users and items. With this understanding, we propose a novel aggregation paradigm named collaborative information aggregation, which focuses on sharing collaborative information rather than item parameters. Based on this new paradigm, we introduce the federated collaborative information aggregation (FedCIA) method for privacy-preserving recommendation. This method requires each client to upload item similarity matrices for aggregation, which allows clients to align their local models without constraining embeddings to a unified vector space. As a result, it mitigates information loss caused by direct summation, preserves the personalized embedding distributions of individual clients, and supports the aggregation of parameter-free models. Theoretical analysis and experimental results on real-world datasets demonstrate the superior performance of FedCIA compared with the state-of-the-art federated recommendation algorithms. Code is available at https://github.com/Mingzhe-Han/FedCIA.

Enhancing Cross-Domain Recommendations with Memory-Optimized LLM-Based User Agents

Large Language Model (LLM)-based user agents have emerged as a powerful tool for improving recommender systems by simulating user interactions. However, existing methods struggle with cross-domain scenarios due to inefficient memory structures, leading to irrelevant information retention and failure to account for social influence factors such as popularity. To address these limitations, we introduce AgentCF++, a novel framework featuring a dual-layer memory architecture and a two-step fusion mechanism to filter domain-specific preferences effectively. Additionally, we propose interest groups with shared memory, allowing the model to capture the impact of popularity trends on users with similar interests. Through extensive experiments on multiple cross-domain datasets, AgentCF++ demonstrates superior performance over baseline models, highlighting its effectiveness in refining user behavior simulation for recommender systems. Our code is available at https://anonymous.4open.science/r/AgentCF-plus.

Enhancing LLM-Based Recommendations Through Personalized Reasoning

Current recommendation systems powered by large language models (LLMs) often underutilize their reasoning capabilities due to a lack of explicit logical structuring. To address this limitation, we introduce CoT-Rec, a framework that integrates Chain-of-Thought (CoT) reasoning into LLM-driven recommendations by incorporating two crucial processes: user preference analysis and item perception evaluation. CoT-Rec operates in two key phases: (1) personalized data extraction, where user preferences and item perceptions are identified, and (2) personalized data application, where this information is leveraged to refine recommendations. Our experimental analysis demonstrates that CoT-Rec improves recommendation accuracy by making better use of LLMs' reasoning potential. The implementation is publicly available at https://anonymous.4open.science/r/CoT-Rec.

Mitigating Popularity Bias in Collaborative Filtering through Fair Sampling

Recommender systems often suffer from popularity bias, where frequently interacted items are overrepresented in recommendations. This bias stems from propensity factors influencing training data, leading to imbalanced exposure. In this paper, we introduce a Fair Sampling (FS) approach to address this issue by ensuring that both users and items are selected with equal probability as positive and negative instances. Unlike traditional inverse propensity score (IPS) methods, FS does not require propensity estimation, eliminating errors associated with inaccurate calculations. Our theoretical analysis demonstrates that FS effectively neutralizes the influence of propensity factors, achieving unbiased learning. Experimental results validate that FS outperforms state-of-the-art methods in both point-wise and pair-wise recommendation tasks, enhancing recommendation fairness without sacrificing accuracy. The implementation is available at https://anonymous.4open.science/r/Fair-Sampling.

Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning

Residual networks, as discrete approximations of Ordinary Differential Equations (ODEs), have inspired significant advancements in neural network design, including multistep methods, high-order methods, and multi-particle dynamical systems. The precision of the solution to ODEs significantly affects parameter optimization, thereby impacting model performance. In this work, we present a series of advanced explorations of Transformer architecture design to minimize the error compared to the true ``solution.'' First, we introduce a predictor-corrector learning framework to minimize truncation errors, which consists of a high-order predictor and a multistep corrector. Second, we propose an exponential moving average-based coefficient learning method to strengthen our higher-order predictor. Extensive experiments on large-scale machine translation, abstractive summarization, language modeling, and natural language understanding benchmarks demonstrate the superiority of our approach. On the WMT'14 English-German and English-French tasks, our model achieved BLEU scores of 30.95 and 44.27, respectively. Furthermore, on the OPUS multilingual machine translation task, our model surpasses a robust 3.8B DeepNet by an average of 2.9 SacreBLEU, using only 1/3 parameters. Notably, it also beats LLama models by 5.7 accuracy points on the LM Harness Evaluation.