Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains

Tool-augmented multimodal agents show strong benchmark gains, often taken as evidence that agents have learned to use tools. We argue that this interpretation can be premature: a tool-call trace alone does not show whether the tool supplied answer-critical information. We study two representative ``thinking with images'' agents, Thyme and DeepEyesV2, across real-world understanding, OCR, chart understanding, and mathematical reasoning. Each agent is compared with its Tool-Free counterpart and with a Pure-Text Reasoner trained from the same source pool without tool-calling trajectories. Tool access yields little consistent aggregate improvement, does not reliably reduce generated-token cost, and leaves only a small tool-only solved set: 93% of DeepEyesV2's tool-solved problems and 96% of Thyme's are also solved by at least one non-tool setting. Mechanism ablations further show that the full tool-use loop does not consistently outperform either the tool-call format or the returned execution result alone. In the settings we study, the analyzed agents appear to learn tool-calling patterns more reliably than tool-contributed capabilities, suggesting that evaluation should distinguish tool availability from whether tools actually expand what agents can solve.

Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation

Multi-behavior recommendation improves target-behavior prediction by exploiting heterogeneous auxiliary feedback (e.g., view, collect, and cart), yet its robustness is undermined by behavior-dependent noise and inconsistency. We argue that the key bottleneck is a representation-level failure caused by two coupled heterogeneities. First, intra-behavior representation entanglement arises when multi-hop propagation blends incidental signals with true preferences in the embedding space, making coarse spatial denoising unable to suppress noise without sacrificing informative niche signals. Second, inter-behavior reliability heterogeneity complicates cross-behavior fusion because the predictive value of auxiliary behaviors varies across users and contexts. Without reliability calibration, frequent yet unreliable signals may dominate aggregation and cause target-intent drift. To address this bottleneck, we propose Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation (SpectraMB), a target-oriented model that performs representation purification before reliability-aware fusion. SpectraMB introduces Dynamic Feature-Level Spectral Filtering, which re-parameterizes embeddings along the feature dimension into a feature-frequency space and learns view-adaptive spectral modulation under target supervision, enabling component-wise purification without hand-crafted frequency assumptions. It further proposes Global-Context Attention Fusion, which uses a purified global representation as a context anchor to assess view compatibility and perform reliability-aware aggregation, while a residual global backbone preserves collaborative structure. Extensive experiments on three real-world datasets show that SpectraMB achieves the best results in most evaluation settings and exhibits improved robustness under noisy interactions.

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning

Recent latent visual reasoning methods achieve substantial gains by inserting continuous latent tokens into multimodal language models. These gains are commonly attributed to the tokens encoding visual evidence; recent analyses, however, reveal a paradox: the tokens are loosely tied to the image and contribute little to the answer. Critically, these analyses treat latent tokens as a single unit, obscuring the true source of the gains. We therefore decompose latent tokens into three testable components: latent slots, boundary markers, and format, and develop a state-of-the-art method as a probe under favorable conditions. Across six method-stage settings and four perception-heavy benchmarks, latent slots fail every prediction of the visual-memory account. Strikingly, retaining only the boundary markers preserves 78 to 100% of the gain in several settings, while the model attends to the image more narrowly at latent positions than at answer positions. The gain therefore comes from boundary markers, format, and this attention pattern, not from latent slots. How each method engages this mechanism depends on its training supervision: at matched accuracy, mechanisms can still differ markedly. Latent visual reasoning thus needs evaluation not only by accuracy but by what the model actually relies on.

TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety

Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. Existing turn-level or short-context detectors struggle to reliably retain and aggregate such evidence over extended horizons. We reframe long-horizon agent safety detection as trajectory-level evidence compression and propose Trajectory Risk-Aware Compression for Long-Horizon Agent Safety (TRACE). TRACE uses a Compressor-Reader design: the Compressor encodes the full trajectory into a compact latent evidence state under trajectory-level supervision, and the Reader judges the raw trajectory with this latent evidence state as a safety reference. This design helps aggregate dispersed risk cues and reduce premature evidence loss. Across ASSEBench, Pre-Ex-Bench, and R-Judge, TRACE achieves the best accuracy on all evaluated backbones, improving over strong baselines by up to 12.6 percentage points. On LongSafety, TRACE shows smaller performance degradation as context length grows. Attention visualizations and case studies suggest that the compressed reference helps the Reader focus on risk-critical segments and recover cross-step evidence. Code is available at https://github.com/Peregrine123/TRACE_official.

Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts

Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms that support these behaviors remain insufficiently understood. In this work, we show that across a wide range of open-weight Transformers, a subset of neurons remains consistently highly activated during inference across tasks of multiple capability dimensions. By probing along the cross-task activation strength, an extremely sparse subset is isolated, whose removal causes a collapse in model behavior, which we term keystone neurons. Our analysis reveals that keystone neurons are a stable and intrinsic neuron subset of the model that is largely established during pretraining. The parameters associated with these neurons are tightly calibrated during the training process, and their precise values are critical for the capabilities of the model. Building on these insights, we propose a supervised fine-tuning approach that updates only keystone neurons, achieving task gains comparable to or even better than full-parameter fine-tuning while better preserving performance in other capability dimensions, despite modifying a much smaller number of parameters.

PetroBench: A Benchmark for Large Language Models in Petroleum Engineering

Large Language Models are increasingly applied in the petroleum industry, highlighting the need for a domain-specific evaluation framework. This study develops a benchmark for LLMs in petroleum engineering, including a three-stage process of data preprocessing, quality filtering, and multi-model validation. Using expert review, a standardized question bank with strong domain relevance and discriminative capability was constructed. The benchmark covers production, reservoir, and drilling engineering, with 1,200 questions across multiple-choice, true or false, term definition, and short-answer formats. Eight mainstream LLMs were evaluated under a unified API environment. Results show that models performed better on subjective than objective questions, indicating weaknesses in factual knowledge discrimination. The highest accuracies for multiple-choice and true or false questions were 65.3% and 74.3%, respectively. Gemini-3-Pro, Kimi-K2.5, and Claude-Opus-4.6-Thinking achieved the best overall scores of 72%-74%. Models performed best in production engineering and weakest in reservoir engineering. Chinese models showed advantages in multiple-choice questions, while international models performed slightly better in short-answer questions. The benchmark provides a reproducible and practical reference for evaluating and deploying LLMs in petroleum engineering.

What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation

Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly understood. Prior work has largely studied generation-time behavior. We instead ask a probe-time question: given a fixed rationale in context, what in that text changes the answer? We identify two complementary sources of the gain. First, even a globally word-shuffled rationale substantially outperforms the no-rationale baseline, indicating a strong lexical activation effect. More importantly, the additional gain from structured text appears to arise less from sentence-level logical ordering and more from short-range token adjacency. Preserving contiguous windows of just $n^\star{=}2$--$3$ tokens recovers most of the remaining gain toward full CoT performance. Supporting experiments rule out copying of explicit answer declarations or answer values, as well as full grammatical realization, as primary drivers. Further generalization experiments show that the qualitative pattern remains stable across multiple model families, parameter scales, and datasets. These results support a local co-occurrence activation (LCA) account of probe-time CoT, in which the observed gains appear to arise primarily from lexical activation and short-range token co-occurrence rather than sentence-level logical derivation.

Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments

Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often exhibit notable degradation when deployed in real-world settings, where environments are inherently stochastic and imperfect. We argue that this discrepancy arises from a fundamental mismatch between idealized training settings and real-world interaction dynamics, where current paradigms rely on carefully curated task instructions and stable, well-controlled environments. To address this gap, we propose NoisyAgent, an agentic training framework that explicitly incorporates environmental imperfections into the agent learning process. We identify two major sources of interaction noise in real-world scenarios: user noise, which captures ambiguity and variability in user interaction, and tool noise, which reflects failures and anomalies in tool execution. We introduce such perturbations into the training pipeline by modifying user interaction patterns and simulating tool execution results within the training environment. To stabilize training while encouraging agents to handle increasingly challenging imperfections, noise is applied to only a subset of rollouts and progressively increased in difficulty as the model adapts to the current noise level. Extensive experiments demonstrate that our approach consistently improves agent robustness under noisy and dynamic environments. Our analysis reveals that training under noise conditions also yields performance gains on idealized benchmarks, suggesting that controlled exposure to environmental noise promotes more generalizable reasoning and decision-making behaviors. Our findings highlight the importance of modeling interaction imperfections for bridging the gap between agent training and real-world deployment.

VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions

Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such settings increasingly depends on understanding the user beyond what is explicitly stated, as user intent is often reflected in fragmented daily interactions and requires both personalized modeling and proactive interaction. However, existing agent benchmarks primarily evaluate reasoning and tool use, largely overlooking the challenges of inferring and leveraging user preferences in realistic scenarios. To address this gap, we introduce VitaBench 2.0, a benchmark for evaluating personalized and proactive agent behavior in long-term user interactions. In VitaBench 2.0, tasks are organized as temporally ordered sequences for individual users, where preferences are embedded in fragmented and heterogeneous interactions. Successful completion of tasks requires the agent to continuously extract, utilize, and update user preferences from these interactions. We further evaluate proactiveness through tasks that require agents to recognize missing information and actively acquire it from users or environments before making decisions. To support systematic analysis, we provide an extensible memory interface that enables controlled comparison across different memory architectures. We benchmark a diverse set of frontier proprietary and open-source LLMs. Results show that real-world personalization remains highly challenging even for state-of-the-art models, revealing a substantial gap between current capabilities and practical requirements. Extensive analysis further reveals the failure modes and capability bottlenecks of current agents in real-world personalized decision-making, providing insights for future model improvements.

MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots

This paper presents MuGen, a data-driven framework for learning and deploying multi-skill locomotion on humanoid robots. MuGen enables a robot to perform expressive motions like humans under the guidance of example motion sequences. To achieve this, we employ vector-quantized autoencoders (VQ-VAEs) trained with model-based reinforcement learning, resulting in a generative representation of locomotion that captures key patterns of human motion from hours of heterogeneous human performance data. We employ a teacher-student learning framework and develop a new policy distillation strategy to enable a deployable student policy learning this efficient latent representation. This policy allows the robot to track and mimic unseen human motions and further enables the robot to reuse the learned latent space for other tasks. We demonstrate the effectiveness of our framework through a diverse set of motions and accurate execution.