Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives

The rapid advancement of Large Language Models (LLMs) is revolutionizing AI for Games by enabling open-ended and fluid interactive storytelling. However, existing research has largely overlooked the critical challenge of maintaining long-horizon logical consistency and narrative integrity against unconstrained user interventions. To address this, we formulate this challenge as Narrative Commitment Preservation (NCP), and take interactive narrative as our testbed. We introduce NCP-Bench, a benchmark of 100 narrative environments derived from movie synopses. Each environment includes a structured narrative specification (trajectory, commitments, and initial facts) that we can automatically check throughout the interaction between the player agent and the narrator agent. Experiments across state-of-the-art LLMs reveal a substantial long-horizon consistency gap: high linguistic quality does not guarantee commitment preservation; even strong models frequently generate logically conflicting content under adversarial interventions, with the best-performing model (GPT-5.2) achieving only 42% survival rate after 20 turns and fact conflict rates ranging from 40% to 68% across models, and only isolated runs satisfying all achievement commitments within the 100-turn limit.

Tired Actor: Fatigue-Informed Character Control

Replicating human behavior with physics simulation has been a long-expected goal in character animation. Existing efforts have achieved impressive performance in imitating a wide span of general motions. However, most existing efforts could still suffer from unnatural movements due to the lack of biomechanical and physiological priors. Given this, we project our sights to advances in behavioral energetics, which demonstrate how energy use shapes human movements. In contrast, current character controllers typically assume the character is equipped with infinite energy over time. Inspired by these, we propose to adopt fatigue as a proxy of the finite energy limit, inject it into general character animation, and thoroughly investigate how fatigue introduces new characteristics to physics-based character control. Leveraging the Three-Compartment Controller (3CC) model, we managed to obtain a policy for general motion imitation under different fatigue statuses. Furthermore, extensive analyses are conducted to demonstrate how fatigue could influence the naturalness, scalability, and robustness of character animation. Our code will be made public.

Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents

Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Existing agents typically formulate restoration as a tool-using process, where the agent perceives degradations, searches candidate tools, executes restoration operations, and revises the plan through reflection or rollback. However, their knowledge is often stored as static tool descriptions, manually defined degradation priors, or unstructured textual summaries, which limits the accumulation, verification, revision, and forgetting of restoration knowledge over long-term experience. In this paper, we propose Causal-AgentIR, a hierarchical multi-agent framework with self-evolving causal memory for collective image restoration intelligence. Instead of representing restoration experience as isolated textual records, Causal-AgentIR organizes degradation patterns, image regions, restoration tools, actions, quality changes, and user preferences into a structured causal memory graph. This graph supports graph-based retrieval and multi-hop causal reasoning, enabling agents to infer how specific restoration operations or tool sequences affect restoration quality under different degradation conditions. The framework further organizes multiple agents into a collaborative system, including planning, degradation analysis, tool expertise, causal memory reasoning, outcome critique, and memory curation. Through this design, restoration experience can be added, updated, merged, reinforced, ignored, or discarded according to observed quality changes and feedback, allowing the agent to maintain reliable and transferable restoration knowledge. Extensive experiments demonstrate the effectiveness of the proposed framework.

Learning Adaptive Dynamical Features via Multi-$τ$ Liquid-Mamba for All-in-one Image Restoration

Image restoration aims to recover high-quality images from degraded observations. Recent Mamba-based image restoration models have demonstrated strong potential in modeling long-range dependencies with linear complexity. However, most existing designs still rely on a single state-evolution timescale, which limits their adaptability to spatially heterogeneous and task-dependent degradation patterns in all-in-one image restoration. In this paper, we propose Multi-$τ$ Liquid-Mamba, an adaptive state space module that introduces input-conditioned multi-timescale liquid discretization into selective state space modeling. Instead of changing the overall selective scan pipeline, the proposed module modulates the effective discretization steps of multiple dynamical branches and adaptively fuses their responses according to degradation-aware gating weights. This design allows the model to capture both fast-varying local details and slowly evolving global structures while preserving the linear scaling property of Mamba with respect to sequence length. Importantly, Multi-$τ$ Liquid-Mamba modulates the effective transition dynamics while preserving the original selective parameterization and hardware-efficient selective scan mechanism, making it a plug-and-play module that can be seamlessly integrated into existing Mamba-based architectures. Built upon this framework, we develop a Multi-$τ$ Liquid-Mamba Image Restoration Network (MLMIR) for all-in-one image restoration. Extensive experiments on a wide range of restoration benchmarks demonstrate that MLMIR consistently achieves state-of-the-art performance in all-in-one image restoration while remaining highly competitive in task-aligned restoration settings.

The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference

Large language models (LLMs) are increasingly deployed in multilingual settings, yet the energy costs of serving these models across different languages remain poorly understood. We present a systematic study of inference energy consumption across languages with ML.Energy framework (Chung et al., 2026). We find striking disparities: energy consumption per output token varies by up to 8.3 times across languages, while total energy for a fixed set of requests varies by up to 179 times between the cheapest (English, 17.6 kJ) and the most expensive (Pashto, 3,147 kJ) languages. Our analysis shows that this disparity is driven by two compounding factors: (1) higher per-token energy costs for languages using complex or rare scripts, and (2) more tokens generated for low-resource languages. Moreover, we find a double cost + performance penalty: languages with the highest energy footprints also tend to achieve the lowest task accuracy. We reveal that the energy divide persists across models, hardware, and tasks, suggesting a systemic energy inequity in multilingual LLM deployment. Finally, we recommend that the community treat energy as a first-class evaluation axis, extend reporting checklists and model cards to include it, and adopt deployment-side mitigations for better energy efficiency.

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment. Instead, this paper highlights the need for principled approaches to more advanced alignment. Alignment aims to ensure that large language models (LLMs) behave safely and reliably, including by avoiding unsafe inferences. However, we show that such safety-oriented behaviors can misfire: models may reject warranted conclusions even when they are explicitly supported by context. We call this failure mode misfired alignment, where alignment-induced changes cause LLMs to override explicit evidence. To quantify this phenomenon, specifically on stereotype-related alignment, we introduce VETO, a benchmark consisting of 2,032 BBQ-derived contrastive pairs, and define a new metric, Misfired Alignment Rate (MAR), which measures on a 0 to 100 scale how often a model fails on a stereotype-related question but succeeds on its contrastive counterpart. We benchmark 25 LLMs on VETO, and show that all LLMs, including the most recent ones, exhibit non-trivial (4.7 to 18.9%) MARs while all human participants achieve 0.0% MAR. Controlled priming experiments further show that alignment-induced cues can substantially amplify MAR across LLMs, indicating that these failures are not merely artifacts of individual examples but can be induced by safety-related framing. Mechanistic analyses on open-weight LLMs reveal late-layer suppression of evidence-supported answers, and comparisons between instruct and base LLMs suggest that this suppression emerges after instruction training. These findings show that current alignment methods can overgeneralize surface-level safety cues, to the point of overriding objective evidence, motivating more work on alignment objectives that better preserve contextual grounding.

Kwai Keye-VL-2.0 Technical Report

We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To address the challenges of ultra-long contexts, information redundancy, and prohibitive computational costs inherent in hour-level videos, Keye-VL-2.0 is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based multimodal architectures, enabling lossless 256K context processing while capturing critical frames and long-range temporal dependencies. This architecture is underpinned by a highly optimized training and inference infrastructure, including scalable video I/O, heterogeneous ViT-LM parallelism, and custom DSA kernels that significantly maximize throughput and minimize computational overhead. Furthermore, to overcome the algorithmic dilemma of catastrophic forgetting during multi-task alignment, we introduce Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) paired with Context-RL and Video-RL. By distilling dense token-level teacher feedback from on-policy rollouts back into the MoE backbone, which activates only 3B parameters, Keye-VL-2.0 natively empowers advanced agent collaboration across Code, Tool, and Search scenarios with multimodal self-correction. Extensive evaluations across video understanding, temporal grounding, reasoning, STEM, and agent benchmarks demonstrate that Keye-VL-2.0-30B-A3B achieves state-of-the-art performance among models of similar scale, particularly excelling in fine-grained temporal localization on TimeLens and long-video comprehension on Video-MME-v2 and LongVideoBench. We release our model checkpoints to accelerate community progress toward scalable and robust multimodal agentic applications.

SciPaths: Forecasting Pathways to Scientific Discovery

Scientific progress depends on sequences of enabling contributions, yet existing AI4Science benchmarks largely focus on citation prediction, literature retrieval, or idea generation rather than the dependencies that make progress possible. In this paper, we introduce discovery pathway forecasting: given a target scientific contribution and the prior literature available at a specified time, the task is to (1) identify the enabling contributions required to realize it and (2) ground each in prior work when such prior work exists. We present SciPaths, a benchmark of 262 expert-annotated gold pathways and 2,444 silver pathways constructed from machine learning and natural language processing papers, where each pathway records enabling contributions, roles, rationales, and prior-work groundings or unmapped decisions. Evaluating frontier and open-weight language models, we find that the best model reaches only 0.189 F1 under strict semantic matching, with core methodological dependencies hardest to recover. Prior-work grounding improves substantially when gold enabling contributions are provided, showing that decomposition quality is a major bottleneck for end-to-end pathway recovery. SciPaths therefore shifts evaluation toward a missing capability in scientific forecasting: reasoning backward from a target contribution to the enabling scientific building blocks and prior-work dependencies that make it feasible.

UniSTOK: Uniform Inductive Spatio-Temporal Kriging

Spatio-temporal kriging aims to infer signals at unobserved locations from observed sensors and is critical to applications such as transportation and environmental monitoring. In practice, however, observed sensors themselves often exhibit heterogeneous missingness, forcing inductive kriging models to rely on crudely imputed inputs. This setting brings three key challenges: (1) it is unclear whether an value is a true signal or a missingness-induced artifact; (2) missingness is highly heterogeneous across sensors and time; (3) missing observations distort the local spatio-temporal structure. To address these issues, we propose Uniform Inductive Spatio-Temporal Kriging (UniSTOK), a plug-and-play framework that enhances existing inductive kriging backbones under missing observation. Our framework forms a dual-branch input consisting of the original observations and a jigsaw-augmented counterpart that synthesizes proxy signals only at missing entries. The two branches are then processed in parallel by a shared spatio-temporal backbone with explicit missingness mask modulation. Their outputs are finally adaptively fused via dual-channel attention. Experiments on multiple real-world datasets under diverse missing patterns demonstrate consistent and significant improvements.

The Automatic Verification of Image-Text Claims (AVerImaTeC) Shared Task

The Automatic Verification of Image-Text Claims (AVerImaTeC) shared task aims to advance system development for retrieving evidence and verifying real-world image-text claims. Participants were allowed to either employ external knowledge sources, such as web search engines, or leverage the curated knowledge store provided by the organizers. System performance was evaluated using the AVerImaTeC score, defined as a conditional verdict accuracy in which a verdict is considered correct only when the associated evidence score exceeds a predefined threshold. The shared task attracted 14 submissions during the development phase and 6 submissions during the testing phase. All participating systems in the testing phase outperformed the baseline provided. The winning team, HUMANE, achieved an AVerImaTeC score of 0.5455. This paper provides a detailed description of the shared task, presents the complete evaluation results, and discusses key insights and lessons learned.