Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning

Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks. However, standard GRPO employs a coarse-grained credit assignment mechanism that propagates group-level rewards uniformly to to every token in a sequence, neglecting the varying contribution of individual reasoning steps. We address this limitation by introducing Outcome-grounded Advantage Reshaping (OAR), a fine-grained credit assignment mechanism that redistributes advantages based on how much each token influences the model's final answer. We instantiate OAR via two complementary strategies: (1) OAR-P, which estimates outcome sensitivity through counterfactual token perturbations, serving as a high-fidelity attribution signal; (2) OAR-G, which uses an input-gradient sensitivity proxy to approximate the influence signal with a single backward pass. These importance signals are integrated with a conservative Bi-Level advantage reshaping scheme that suppresses low-impact tokens and boosts pivotal ones while preserving the overall advantage mass. Empirical results on extensive mathematical reasoning benchmarks demonstrate that while OAR-P sets the performance upper bound, OAR-G achieves comparable gains with negligible computational overhead, both significantly outperforming a strong GRPO baseline, pushing the boundaries of critic-free LLM reasoning.

Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process

We propose LLM-PeerReview, an unsupervised LLM Ensemble method that selects the most ideal response from multiple LLM-generated candidates for each query, harnessing the collective wisdom of multiple models with diverse strengths. LLM-PeerReview is built on a novel, peer-review-inspired framework that offers a clear and interpretable mechanism, while remaining fully unsupervised for flexible adaptability and generalization. Specifically, it operates in three stages: For scoring, we use the emerging LLM-as-a-Judge technique to evaluate each response by reusing multiple LLMs at hand; For reasoning, we can apply a principled graphical model-based truth inference algorithm or a straightforward averaging strategy to aggregate multiple scores to produce a final score for each response; Finally, the highest-scoring response is selected as the best ensemble output. LLM-PeerReview is conceptually simple and empirically powerful. The two variants of the proposed approach obtain strong results across four datasets, including outperforming the recent advanced model Smoothie-Global by 6.9% and 7.3% points, respectively.

Large Model Enabled Embodied Intelligence for 6G Integrated Perception, Communication, and Computation Network

The advent of sixth-generation (6G) places intelligence at the core of wireless architecture, fusing perception, communication, and computation into a single closed-loop. This paper argues that large artificial intelligence models (LAMs) can endow base stations with perception, reasoning, and acting capabilities, thus transforming them into intelligent base station agents (IBSAs). We first review the historical evolution of BSs from single-functional analog infrastructure to distributed, software-defined, and finally LAM-empowered IBSA, highlighting the accompanying changes in architecture, hardware platforms, and deployment. We then present an IBSA architecture that couples a perception-cognition-execution pipeline with cloud-edge-end collaboration and parameter-efficient adaptation. Subsequently,we study two representative scenarios: (i) cooperative vehicle-road perception for autonomous driving, and (ii) ubiquitous base station support for low-altitude uncrewed aerial vehicle safety monitoring and response against unauthorized drones. On this basis, we analyze key enabling technologies spanning LAM design and training, efficient edge-cloud inference, multi-modal perception and actuation, as well as trustworthy security and governance. We further propose a holistic evaluation framework and benchmark considerations that jointly cover communication performance, perception accuracy, decision-making reliability, safety, and energy efficiency. Finally, we distill open challenges on benchmarks, continual adaptation, trustworthy decision-making, and standardization. Together, this work positions LAM-enabled IBSAs as a practical path toward integrated perception, communication, and computation native, safety-critical 6G systems.

Chirp Delay-Doppler Domain Modulation Based Joint Communication and Radar for Autonomous Vehicles

This paper introduces a sensing-centric joint communication and millimeter-wave radar paradigm to facilitate collaboration among intelligent vehicles. We first propose a chirp waveform-based delay-Doppler quadrature amplitude modulation (DD-QAM) that modulates data across delay, Doppler, and amplitude dimensions. Building upon this modulation scheme, we derive its achievable rate to quantify the communication performance. We then introduce an extended Kalman filter-based scheme for four-dimensional (4D) parameter estimation in dynamic environments, enabling the active vehicles to accurately estimate orientation and tangential-velocity beyond traditional 4D radar systems. Furthermore, in terms of communication, we propose a dual-compensation-based demodulation and tracking scheme that allows the passive vehicles to effectively demodulate data without compromising their sensing functions. Simulation results underscore the feasibility and superior performance of our proposed methods, marking a significant advancement in the field of autonomous vehicles. Simulation codes are provided to reproduce the results in this paper: \href{https://github.com/LiZhuoRan0/2026-IEEE-TWC-ChirpDelayDopplerModulationISAC}{https://github.com/LiZhuoRan0}.

Radiation Pattern Reconfigurable FAS-Empowered Interference-Resilient UAV Communication

The widespread use of uncrewed aerial vehicles (UAVs) has propelled the development of advanced techniques on countering unauthorized UAV flights. However, the resistance of legal UAVs to illegal interference remains under-addressed. This paper proposes radiation pattern reconfigurable fluid antenna systems (RPR-FAS)-empowered interference-resilient UAV communication scheme. This scheme integrates the reconfigurable pixel antenna technology, which provides each antenna with an adjustable radiation pattern. Therefore, RPR-FAS can enhance the angular resolution of a UAV with a limited number of antennas, thereby improving spectral efficiency (SE) and interference resilience. Specifically, we first design dedicated radiation pattern adapted from 3GPP-TR-38.901, where the beam direction and half power beamwidth are tailored for UAV communications. Furthermore, we propose a low-storage-overhead orthogonal matching pursuit multiple measurement vectors algorithm, which accurately estimates the angle-of-arrival (AoA) of the communication link, even in the single antenna case. Particularly, by utilizing the Fourier transform to the radiation pattern gain matrix, we design a dimension-reduction technique to achieve 1--2 order-of-magnitude reduction in storage requirements. Meanwhile, we propose a maximum likelihood interference AoA estimation method based on the law of large numbers, so that the SE can be further improved. Finally, alternating optimization is employed to obtain the optimal uplink radiation pattern and combiner, while an exhaustive search is applied to determine the optimal downlink pattern, complemented by the water-filling algorithm for beamforming. Comprehensive simulations demonstrate that the proposed schemes outperform traditional methods in terms of angular sensing precision and spectral efficiency.

OM2P: Offline Multi-Agent Mean-Flow Policy

Generative models, especially diffusion and flow-based models, have been promising in offline multi-agent reinforcement learning. However, integrating powerful generative models into this framework poses unique challenges. In particular, diffusion and flow-based policies suffer from low sampling efficiency due to their iterative generation processes, making them impractical in time-sensitive or resource-constrained settings. To tackle these difficulties, we propose OM2P (Offline Multi-Agent Mean-Flow Policy), a novel offline MARL algorithm to achieve efficient one-step action sampling. To address the misalignment between generative objectives and reward maximization, we introduce a reward-aware optimization scheme that integrates a carefully-designed mean-flow matching loss with Q-function supervision. Additionally, we design a generalized timestep distribution and a derivative-free estimation strategy to reduce memory overhead and improve training stability. Empirical evaluations on Multi-Agent Particle and MuJoCo benchmarks demonstrate that OM2P achieves superior performance, with up to a 3.8x reduction in GPU memory usage and up to a 10.8x speed-up in training time. Our approach represents the first to successfully integrate mean-flow model into offline MARL, paving the way for practical and scalable generative policies in cooperative multi-agent settings.

Reparameterization Proximal Policy Optimization

Reparameterization policy gradient (RPG) is promising for improving sample efficiency by leveraging differentiable dynamics. However, a critical barrier is its training instability, where high-variance gradients can destabilize the learning process. To address this, we draw inspiration from Proximal Policy Optimization (PPO), which uses a surrogate objective to enable stable sample reuse in the model-free setting. We first establish a connection between this surrogate objective and RPG, which has been largely unexplored and is non-trivial. Then, we bridge this gap by demonstrating that the reparameterization gradient of a PPO-like surrogate objective can be computed efficiently using backpropagation through time. Based on this key insight, we propose Reparameterization Proximal Policy Optimization (RPO), a stable and sample-efficient RPG-based method. RPO enables multiple epochs of stable sample reuse by optimizing a clipped surrogate objective tailored for RPG, while being further stabilized by Kullback-Leibler (KL) divergence regularization and remaining fully compatible with existing variance reduction methods. We evaluate RPO on a suite of challenging locomotion and manipulation tasks, where experiments demonstrate that our method achieves superior sample efficiency and strong performance.

Proxy-Free GFlowNet

Generative Flow Networks (GFlowNets) are a promising class of generative models designed to sample diverse, high-reward structures by modeling distributions over compositional objects. In many real-world applications, obtaining the reward function for such objects is expensive, time-consuming, or requires human input, making it necessary to train GFlowNets from historical datasets. Most existing methods adopt a model-based approach, learning a proxy model from the dataset to approximate the reward function. However, this strategy inherently ties the quality of the learned policy to the accuracy of the proxy, introducing additional complexity and uncertainty into the training process. To overcome these limitations, we propose \textbf{Trajectory-Distilled GFlowNet (TD-GFN)}, a \emph{proxy-free} training framework that eliminates the need for out-of-dataset reward queries. Our method is motivated by the key observation that different edges in the associated directed acyclic graph (DAG) contribute unequally to effective policy learning. TD-GFN leverages inverse reinforcement learning to estimate edge-level rewards from the offline dataset, which are then used to ingeniously prune the DAG and guide backward trajectory sampling during training. This approach directs the policy toward high-reward regions while reducing the complexity of model fitting. Empirical results across multiple tasks show that TD-GFN trains both efficiently and reliably, significantly outperforming existing baselines in convergence speed and sample quality.

On Path to Multimodal Historical Reasoning: HistBench and HistAgent

Recent advances in large language models (LLMs) have led to remarkable progress across domains, yet their capabilities in the humanities, particularly history, remain underexplored. Historical reasoning poses unique challenges for AI, involving multimodal source interpretation, temporal inference, and cross-linguistic analysis. While general-purpose agents perform well on many existing benchmarks, they lack the domain-specific expertise required to engage with historical materials and questions. To address this gap, we introduce HistBench, a new benchmark of 414 high-quality questions designed to evaluate AI's capacity for historical reasoning and authored by more than 40 expert contributors. The tasks span a wide range of historical problems-from factual retrieval based on primary sources to interpretive analysis of manuscripts and images, to interdisciplinary challenges involving archaeology, linguistics, or cultural history. Furthermore, the benchmark dataset spans 29 ancient and modern languages and covers a wide range of historical periods and world regions. Finding the poor performance of LLMs and other agents on HistBench, we further present HistAgent, a history-specific agent equipped with carefully designed tools for OCR, translation, archival search, and image understanding in History. On HistBench, HistAgent based on GPT-4o achieves an accuracy of 27.54% pass@1 and 36.47% pass@2, significantly outperforming LLMs with online search and generalist agents, including GPT-4o (18.60%), DeepSeek-R1(14.49%) and Open Deep Research-smolagents(20.29% pass@1 and 25.12% pass@2). These results highlight the limitations of existing LLMs and generalist agents and demonstrate the advantages of HistAgent for historical reasoning.

Chirp Delay-Doppler Domain Modulation: A New Paradigm of Integrated Sensing and Communication for Autonomous Vehicles

Autonomous driving is reshaping the way humans travel, with millimeter wave (mmWave) radar playing a crucial role in this transformation to enabe vehicle-to-everything (V2X). Although chirp is widely used in mmWave radar systems for its strong sensing capabilities, the lack of integrated communication functions in existing systems may limit further advancement of autonomous driving. In light of this, we first design ``dedicated chirps" tailored for sensing chirp signals in the environment, facilitating the identification of idle time-frequency resources. Based on these dedicated chirps, we propose a chirp-division multiple access (Chirp-DMA) scheme, enabling multiple pairs of mmWave radar transceivers to perform integrated sensing and communication (ISAC) without interference. Subsequently, we propose two chirp-based delay-Doppler domain modulation schemes that enable each pair of mmWave radar transceivers to simultaneously sense and communicate within their respective time-frequency resource blocks. The modulation schemes are based on different multiple-input multiple-output (MIMO) radar schemes: the time division multiplexing (TDM)-based scheme offers higher communication rates, while the Doppler division multiplexing (DDM)-based scheme is suitable for working in a lower signal-to-noise ratio range. We then validate the effectiveness of the proposed DDM-based scheme through simulations. Finally, we present some challenges and issues that need to be addressed to advance ISAC in V2X for better autonomous driving. Simulation codes are provided to reproduce the results in this paper: \href{https://github.com/LiZhuoRan0/2025-IEEE-Network-ChirpDelayDopplerModulationISAC}{https://github.com/LiZhuoRan0}.