Behavior Knowledge Merge in Reinforced Agentic Models

Reinforcement learning (RL) is central to post-training, particularly for agentic models that require specialized reasoning behaviors. In this setting, model merging offers a practical mechanism for integrating multiple RL-trained agents from different tasks into a single generalist model. However, existing merging methods are designed for supervised fine-tuning (SFT), and they are suboptimal to preserve task-specific capabilities on RL-trained agentic models. The root is a task-vector mismatch between RL and SFT: on-policy RL induces task vectors that are highly sparse and heterogeneous, whereas SFT-style merging implicitly assumes dense and globally comparable task vectors. When standard global averaging is applied under this mismatch, RL's non-overlapping task vectors that encode critical task-specific behaviors are reduced and parameter updates are diluted. To address this issue, we propose Reinforced Agent Merging (RAM), a distribution-aware merging framework explicitly designed for RL-trained agentic models. RAM disentangles shared and task-specific unique parameter updates, averaging shared components while selectively preserving and rescaling unique ones to counteract parameter update dilution. Experiments across multiple agent domains and model architectures demonstrate that RAM not only surpasses merging baselines, but also unlocks synergistic potential among agents to achieve performance superior to that of specialized agents in their domains.

Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization

Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thinking approaches often lead to overthinking, where models produce excessively verbose responses even for simple queries, resulting in test-time inefficiency and even degraded accuracy. Prior work has attempted to mitigate this issue via adaptive reasoning strategies, but these methods largely overlook a fundamental bottleneck: visual perception failures. We argue that stable reasoning critically depends on low-level visual grounding, and that reasoning errors often originate from imperfect perception rather than insufficient deliberation. To address this limitation, we propose Gated Perception-Reasoning Optimization (GPRO), a meta-reasoning controller that dynamically routes computation among three decision paths at each generation step: a lightweight fast path, a slow perception path for re-examining visual inputs, and a slow reasoning path for internal self-reflection. To learn this distinction, we derive large-scale failure attribution supervision from approximately 790k samples, using teacher models to distinguish perceptual hallucinations from reasoning errors. We then train the controller with multi-objective reinforcement learning to optimize the trade-off between task accuracy and computational cost under uncertainty. Experiments on five benchmarks demonstrate that GPRO substantially improves both accuracy and efficiency, outperforming recent slow-thinking methods while generating significantly shorter responses.

PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

Text-to-audio-video (T2AV) generation underpins a wide range of applications demanding realistic audio-visual content, including virtual reality, world modeling, gaming, and filmmaking. However, existing T2AV models remain incapable of generating physically plausible sounds, primarily due to their limited understanding of physical principles. To situate current research progress, we present PhyAVBench, a challenging audio physics-sensitivity benchmark designed to systematically evaluate the audio physics grounding capabilities of existing T2AV models. PhyAVBench comprises 1,000 groups of paired text prompts with controlled physical variables that implicitly induce sound variations, enabling a fine-grained assessment of models' sensitivity to changes in underlying acoustic conditions. We term this evaluation paradigm the Audio-Physics Sensitivity Test (APST). Unlike prior benchmarks that primarily focus on audio-video synchronization, PhyAVBench explicitly evaluates models' understanding of the physical mechanisms underlying sound generation, covering 6 major audio physics dimensions, 4 daily scenarios (music, sound effects, speech, and their mix), and 50 fine-grained test points, ranging from fundamental aspects such as sound diffraction to more complex phenomena, e.g., Helmholtz resonance. Each test point consists of multiple groups of paired prompts, where each prompt is grounded by at least 20 newly recorded or collected real-world videos, thereby minimizing the risk of data leakage during model pre-training. Both prompts and videos are iteratively refined through rigorous human-involved error correction and quality control to ensure high quality. We argue that only models with a genuine grasp of audio-related physical principles can generate physically consistent audio-visual content. We hope PhyAVBench will stimulate future progress in this critical yet largely unexplored domain.

How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline

Unmanned Aerial Vehicles (UAVs) offer wide-ranging applications but also pose significant safety and privacy violation risks in areas like airport and infrastructure inspection, spurring the rapid development of Anti-UAV technologies in recent years. However, current Anti-UAV research primarily focuses on RGB, infrared (IR), or RGB-IR videos captured by fixed ground cameras, with little attention to tracking target UAVs from another moving UAV platform. To fill this gap, we propose a new multi-modal visual tracking task termed UAV-Anti-UAV, which involves a pursuer UAV tracking a target adversarial UAV in the video stream. Compared to existing Anti-UAV tasks, UAV-Anti-UAV is more challenging due to severe dual-dynamic disturbances caused by the rapid motion of both the capturing platform and the target. To advance research in this domain, we construct a million-scale dataset consisting of 1,810 videos, each manually annotated with bounding boxes, a language prompt, and 15 tracking attributes. Furthermore, we propose MambaSTS, a Mamba-based baseline method for UAV-Anti-UAV tracking, which enables integrated spatial-temporal-semantic learning. Specifically, we employ Mamba and Transformer models to learn global semantic and spatial features, respectively, and leverage the state space model's strength in long-sequence modeling to establish video-level long-term context via a temporal token propagation mechanism. We conduct experiments on the UAV-Anti-UAV dataset to validate the effectiveness of our method. A thorough experimental evaluation of 50 modern deep tracking algorithms demonstrates that there is still significant room for improvement in the UAV-Anti-UAV domain. The dataset and codes will be available at {\color{magenta}https://github.com/983632847/Awesome-Multimodal-Object-Tracking}.

What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning

Curriculum learning (CL) - ordering training data from easy to hard - has become a popular strategy for improving reasoning in large language models (LLMs). Yet prior work employs disparate difficulty metrics and training setups, leaving open fundamental questions: When does curriculum help? Which direction - forward or reverse - is better? And does the answer depend on what we measure? We address these questions through a unified offline evaluation framework that decomposes curriculum difficulty into five complementary dimensions: Problem Difficulty, Model Surprisal, Confidence Margin, Predictive Uncertainty, and Decision Variability. Through controlled post-training experiments on mathematical reasoning benchmarks with Llama3.1-8B, Mistral-7B, and Gemma3-4B, we find that (i) no curriculum strategy dominates universally - the relative effectiveness of forward versus reverse CL depends jointly on model capability and task complexity; (ii) even within a single metric, samples at different difficulty levels produce distinct gains depending on task demands; and (iii) task-aligned curricula focus on shaping the model's final representations and generalization, whereas inner-state curricula modulate internal states such as confidence and uncertainty. Our findings challenge the notion of a universal curriculum strategy and offer actionable guidance across model and task regimes, with some metrics indicating that prioritizing decision-uncertain samples can further enhance learning outcomes.

Mind the Gap: The Divergence Between Human and LLM-Generated Tasks

Humans constantly generate a diverse range of tasks guided by internal motivations. While generative agents powered by large language models (LLMs) aim to simulate this complex behavior, it remains uncertain whether they operate on similar cognitive principles. To address this, we conducted a task-generation experiment comparing human responses with those of an LLM agent (GPT-4o). We find that human task generation is consistently influenced by psychological drivers, including personal values (e.g., Openness to Change) and cognitive style. Even when these psychological drivers are explicitly provided to the LLM, it fails to reflect the corresponding behavioral patterns. They produce tasks that are markedly less social, less physical, and thematically biased toward abstraction. Interestingly, while the LLM's tasks were perceived as more fun and novel, this highlights a disconnect between its linguistic proficiency and its capacity to generate human-like, embodied goals.We conclude that there is a core gap between the value-driven, embodied nature of human cognition and the statistical patterns of LLMs, highlighting the necessity of incorporating intrinsic motivation and physical grounding into the design of more human-aligned agents.

SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models

While large language models have shown reasoning capabilities, their application to the audio modality, particularly in large audio-language models (ALMs), remains significantly underdeveloped. Addressing this gap requires a systematic approach, involving a capable base model, high-quality reasoning-oriented audio data, and effective training algorithms. In this study, we present a comprehensive solution: we introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotated samples specifically designed for complex reasoning tasks. Building on this resource, we propose SoundMind, a rule-based reinforcement learning (RL) algorithm tailored to endow ALMs with deep bimodal reasoning abilities. By training Qwen2.5-Omni-7B on the ALR dataset using SoundMind, our approach achieves state-of-the-art performance in audio logical reasoning. This work highlights the impact of combining high-quality, reasoning-focused datasets with specialized RL techniques, advancing the frontier of auditory intelligence in language models. Our code and the proposed dataset are available at https://github.com/xid32/SoundMind.

Music's Multimodal Complexity in AVQA: Why We Need More than General Multimodal LLMs

While recent Multimodal Large Language Models exhibit impressive capabilities for general multimodal tasks, specialized domains like music necessitate tailored approaches. Music Audio-Visual Question Answering (Music AVQA) particularly underscores this, presenting unique challenges with its continuous, densely layered audio-visual content, intricate temporal dynamics, and the critical need for domain-specific knowledge. Through a systematic analysis of Music AVQA datasets and methods, this position paper identifies that specialized input processing, architectures incorporating dedicated spatial-temporal designs, and music-specific modeling strategies are critical for success in this domain. Our study provides valuable insights for researchers by highlighting effective design patterns empirically linked to strong performance, proposing concrete future directions for incorporating musical priors, and aiming to establish a robust foundation for advancing multimodal musical understanding. This work is intended to inspire broader attention and further research, supported by a continuously updated anonymous GitHub repository of relevant papers: https://github.com/xid32/Survey4MusicAVQA.

Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Tasks

Large Language Models (LLMs) are increasingly used in tasks such as psychological text analysis and decision-making in automated workflows. However, their reliability remains a concern due to potential biases inherited from their training process. In this study, we examine how different response format: binary versus continuous, may systematically influence LLMs' judgments. In a value statement judgments task and a text sentiment analysis task, we prompted LLMs to simulate human responses and tested both formats across several models, including both open-source and commercial models. Our findings revealed a consistent negative bias: LLMs were more likely to deliver "negative" judgments in binary formats compared to continuous ones. Control experiments further revealed that this pattern holds across both tasks. Our results highlight the importance of considering response format when applying LLMs to decision tasks, as small changes in task design can introduce systematic biases.

ToM-RL: Reinforcement Learning Unlocks Theory of Mind in Small LLMs

Recent advancements in rule-based reinforcement learning (RL), applied during the post-training phase of large language models (LLMs), have significantly enhanced their capabilities in structured reasoning tasks such as mathematics and logical inference. However, the effectiveness of RL in social reasoning, particularly in Theory of Mind (ToM), the ability to infer others' mental states, remains largely unexplored. In this study, we demonstrate that RL methods effectively unlock ToM reasoning capabilities even in small-scale LLMs (0.5B to 7B parameters). Using a modest dataset comprising 3200 questions across diverse scenarios, our RL-trained 7B model achieves 84.50\% accuracy on the Hi-ToM benchmark, surpassing models like GPT-4o and DeepSeek-v3 despite significantly fewer parameters. While smaller models ($\leq$3B parameters) suffer from reasoning collapse, larger models (7B parameters) maintain stable performance through consistent belief tracking. Additionally, our RL-based models demonstrate robust generalization to higher-order, out-of-distribution ToM problems, novel textual presentations, and previously unseen datasets. These findings highlight RL's potential to enhance social cognitive reasoning, bridging the gap between structured problem-solving and nuanced social inference in LLMs.