Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems

Multicultural multi-agent systems are increasingly deployed in globally diverse settings, where different agents are grounded in different cultural backgrounds. Existing cultural evaluation focuses on value alignment: how closely a single agent matches a target culture. Yet alignment is a per-agent property and cannot reveal whether a system, taken as a whole, preserves the cultural plurality it is meant to represent. We propose value diversity as a system-level evaluation axis for multicultural agent systems, defined through the dissimilarity between culturally conditioned agents' responses on a shared value survey. Using the World Values Survey, we evaluate 19 cultures and 18 backbone models across a wide range of system configurations. We find that diversity is largely uncorrelated with alignment, indicating that the two capture complementary system properties, and that current multicultural agent systems fall substantially below human societies in value diversity. Mixed-backbone systems narrow this gap but do not close it, and the gap persists across culture compositions and agent scales. Social interaction further erodes diversity by driving agents toward consensus, and a participatory budgeting case study shows that this homogenization narrows the breadth of collective decision-making. Together, our results establish value diversity as a distinct evaluation axis for multicultural multi-agent systems and reveal a persistent homogenization tendency in current LLM-based societies. Our code and data are publicly available at https://github.com/iNLP-Lab/MultiAgent-Diversity.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability. We introduce Posterior Attack, a single-query jailbreak that bypasses guardrails by prompting the model to generate the exact harmful response its internal classifier would normally flag as unsafe. Through extensive empirical evaluation across 30 open-source LLMs (up to 35B parameters in size) and frontier models (e.g., GPT-5, Claude 4.6), we observe a striking phenomenon: models with superior safety-judgment capabilities are disproportionately more susceptible to this exploitation. To explain this, we formalize the Safety Paradox, analytically showing that monotonic improvements in safety alignment naturally amplify posterior vulnerability. Finally, we establish a causal link via reinforcement learning interventions, exemplifying that artificially degrading a model's safety judgment immunizes it against the attack, whereas enhancing judgment exacerbates the vulnerability. Our findings highlight potential flaws in current alignment paradigms, indicating that defense mechanisms may require further structural refinement.

Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

The rapid evolution of Large Language Models (LLMs) has established cross-lingual versatility as a defining feature of modern systems. However, fine-tuning these models frequently induces negative interference across languages. To address this, we reformulate multilingual fine-tuning as a multi-objective optimization (MOO) problem. Specifically, we introduce Bucket-Level MOO, a scalable distributed framework that applies gradient-based MOO algorithms locally on parameter buckets. This enables conflict-aware updates without the prohibitive communication overhead of reconstructing full gradient vectors. Theoretically, we prove this localized resolution natively enforces Refined Pareto Stationarity, a strictly tighter necessary condition for Pareto optimality. Empirically, Bucket-Level MOO mitigates interference by driving LLMs to construct distinct language-specific dimensions, improving representational separability. Extensive experiments across four base LLMs demonstrate that our method significantly improves both seen and unseen multilingual performance over standard fine-tuning paradigms.

What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems

Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is often left as unconstrained natural language. However, this free-form communication can rapidly inflate token usage, consume the shared context window, and ultimately affect both system performance and inference cost. We analyze five common inter-agent communication strategies across two MAS topologies, finding that no fixed strategy is universally optimal. Instead, effective inter-agent messages consistently preserve action-centered information needed by downstream agents. Building on this, we propose the PACT (Protocolized Action-state Communication and Transmission), which treats inter-agent communication as a public state-update problem and projects each raw agent output into a compact action-state record before it enters shared history. Across different MAS topologies, PACT consistently improves the performance-cost trade-off, achieving comparable or stronger task performance with substantially fewer tokens. The gains extend to production coding harnesses: PACT lifts OpenHands' resolve rate at -10% tokens-per-resolved, and is resolve-neutral on SWE-agent while halving input tokens. Our code is publicly available at https://github.com/iNLP-Lab/PACT.

Collaborative Space Object Detection with Multi-Satellite Viewpoints in LEO Constellations

With the growing number of satellites in low Earth orbit (LEO) constellations, the near-Earth space environment has become increasingly congested, making space object detection (SOD) a pressing challenge for space safety and sustainability. To mitigate collision risks and ensure the continuity of space operations, SOD systems must deliver fast and accurate detection under stringent onboard constraints. In this paper, we investigate the potential of multi-viewpoint observation fusion within a deep learning (DL) framework to enhance SOD performance. We design a practical multi-view pipeline and several input representations for feeding multi-view data into YOLO-based detectors. Our experiments show that using multi-view inputs is feasible in most cases and typically produces better results for mAP50 and mAP50-95. For example, in model YOLOv9-m, single-view compared to a three-view fused RGB setting, mAP50 increases from 0.638 to 0.732, while mAP50-95 improves from 0.227 to 0.276. Compared with the single-view setting, the best three-view grayscale configuration improves mAP50 by 36.3% and mAP50-95 by 46.5%. These findings establish multi-view fusion as a viable and effective strategy for SOD, with broad implications for space situational awareness in LEO constellation deployments.

Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces

Long chain-of-thought (CoT) traces are widely used as supervision for reasoning-oriented LLM SFT, yet answer-correct traces can still lead to markedly different fine-tuning outcomes. We study post-conclusion continuation in answer-correct long-CoT data: a continuation where the answer appears sufficiently supported, but the trace continues with additional reasoning that remains in the supervised target. To test its training effect, we use a delete-only editor to construct answer-preserving suffix removal and compare CoT-based SFT on the original and processed traces. We observe improved SFT outcomes after removing the editor-identified post-conclusion continuation, suggesting that this continuation is harmful to training in our setting. We therefore refer to this empirically supported phenomenon as harmful continuation. Beyond this intervention, we further characterize the removed post-conclusion continuation through uncertainty and hidden-state progress. We observe persistent local uncertainty together with weakened terminal-directional progress, forming an uncertainty--geometry mismatch. Finally, we instantiate Harmful Continuation Cut (HCC), a lightweight boundary proxy that approximates the editor-identified post-conclusion continuation boundary.

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a central bottleneck. Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities. We introduce a "levels x laws" taxonomy organized along two axes. The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence. The second identifies four governing-law regimes: physical, digital, social, and scientific. These regimes determine what constraints a world model must satisfy and where it is most likely to fail. Using this framework, we synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery. We analyze methods, failure modes, and evaluation practices across level-regime pairs, propose decision-centric evaluation principles and a minimal reproducible evaluation package, and outline architectural guidance, open problems, and governance challenges. The resulting roadmap connects previously isolated communities and charts a path from passive next-step prediction toward world models that can simulate, and ultimately reshape, the environments in which agents operate.

Hybrid Beamforming for Subarray-Level Movable Antenna Enhanced MU-MIMO Communications

This study investigates subarray-level movable antenna (MA) architecture for multi-user MIMO (MU-MIMO) systems. Unlike conventional systems with fixed-position antennas (FPAs), the proposed scheme harnesses the additional positional degrees of freedom (DoFs) of movable subarrays to enhance spatial multiplexing capabilities for both multi-user and multi-stream communications. Our objective is to maximize the overall system spectral efficiency by jointly optimizing the hybrid beamforming design and the positions of all subarrays. To tackle this challenging non-convex optimization problem, we first adopt a block diagonalization (BD) based digital precoder to effectively eliminate multi-user interference. Subsequently, the joint optimization of the analog beamformer and the subarray positions is efficiently solved using a sequential interference cancellation (SIC)-based algorithm. Simulation results demonstrate that the proposed SIC-MA method significantly outperforms the benchmark SIC-FPA scheme where subarrays are fixed.

One-shot Compositional 3D Head Avatars with Deformable Hair

We propose a compositional method for constructing a complete 3D head avatar from a single image. Prior one-shot holistic approaches frequently fail to produce realistic hair dynamics during animation, largely due to inadequate decoupling of hair from the facial region, resulting in entangled geometry and unnatural deformations. Our method explicitly decouples hair from the face, modeling these components using distinct deformation paradigms while integrating them into a unified rendering pipeline. Furthermore, by leveraging image-to-3D lifting techniques, we preserve fine-grained textures from the input image to the greatest extent possible, effectively mitigating the common issue of high-frequency information loss in generalized models. Specifically, given a frontal portrait image, we first perform hair removal to obtain a bald image. Both the original image and the bald image are then lifted to dense, detail-rich 3D Gaussian Splatting (3DGS) representations. For the bald 3DGS, we rig it to a FLAME mesh via non-rigid registration with a prior model, enabling natural deformation that follows the mesh triangles during animation. For the hair component, we employ semantic label supervision combined with a boundary-aware reassignment strategy to extract a clean and isolated set of hair Gaussians. To control hair deformation, we introduce a cage structure that supports Position-Based Dynamics (PBD) simulation, allowing realistic and physically plausible transformations of the hair Gaussian primitives under head motion, gravity, and inertial effects. Striking qualitative results, including dynamic animations under diverse head motions, gravity effects, and expressions, showcase substantially more realistic hair behavior alongside faithfully preserved facial details, outperforming state-of-the-art one-shot methods in perceptual realism.

Neural Computers

We propose a new frontier: Neural Computers (NCs) -- an emerging machine form that unifies computation, memory, and I/O in a learned runtime state. Unlike conventional computers, which execute explicit programs, agents, which act over external execution environments, and world models, which learn environment dynamics, NCs aim to make the model itself the running computer. Our long-term goal is the Completely Neural Computer (CNC): the mature, general-purpose realization of this emerging machine form, with stable execution, explicit reprogramming, and durable capability reuse. As an initial step, we study whether early NC primitives can be learned solely from collected I/O traces, without instrumented program state. Concretely, we instantiate NCs as video models that roll out screen frames from instructions, pixels, and user actions (when available) in CLI and GUI settings. These implementations show that learned runtimes can acquire early interface primitives, especially I/O alignment and short-horizon control, while routine reuse, controlled updates, and symbolic stability remain open. We outline a roadmap toward CNCs around these challenges. If overcome, CNCs could establish a new computing paradigm beyond today's agents, world models, and conventional computers.