Large language models (LLMs) have shown strong abilities in reasoning and problem solving, but recent studies reveal that they still struggle with time series reasoning tasks, where outputs are often affected by hallucination or knowledge leakage. In this work we propose TS-Agent, a time series reasoning agent that leverages LLMs strictly for what they excel at, i.e., gathering evidence and synthesizing it into conclusions through step-by-step reasoning, while delegating the extraction of statistical and structural information to time series analytical tools. Instead of mapping time series into text tokens, images, or embeddings, our agent interacts with raw numeric sequences through atomic operators, records outputs in an explicit evidence log, and iteratively refines its reasoning under the guidance of a self-critic and a final quality gate. This design avoids multi-modal alignment training, preserves the native form of time series, ensures interpretability and verifiability, and mitigates knowledge leakage or hallucination. Empirically, we evaluate the agent on established benchmarks. Our experiments show that TS-Agent achieves performance comparable to state-of-the-art LLMs on understanding benchmarks, and delivers significant improvements on reasoning tasks, where existing models often rely on memorization and fail in zero-shot settings.

Efficient use of large language models (LLMs) is critical for deployment at scale: without adaptive routing, systems either overpay for strong models or risk poor performance from weaker ones. Selecting the right LLM for each query is fundamentally an online decision problem: models differ in strengths, prices fluctuate, and users value accuracy and cost differently. Yet most routers are trained offline with labels for all candidate models, an assumption that breaks in deployment, where only the outcome of the chosen model is observed. We bridge this gap with BaRP, a Bandit-feedback Routing with Preferences approach that trains under the same partial-feedback restriction as deployment, while supporting preference-tunable inference: operators can dial the performance/cost trade-off at test time without retraining. Framed as a contextual bandit over prompt features and a user preference vector, our method simulates an online feedback setting during training and adapts its routing decisions to each new prompt, rather than depending on full-information offline supervision. Comprehensive experiments show that our method consistently outperforms strong offline routers by at least 12.46% and the largest LLM by at least 2.45%, and generalizes robustly for unseen tasks.

Coordinating heterogeneous robot teams from free-form natural-language instructions is hard. Language-only planners struggle with long-horizon coordination and hallucination, while purely formal methods require closed-world models. We present FLEET, a hybrid decentralized framework that turns language into optimized multi-robot schedules. An LLM front-end produces (i) a task graph with durations and precedence and (ii) a capability-aware robot--task fitness matrix; a formal back-end solves a makespan-minimization problem while the underlying robots execute their free-form subtasks with agentic closed-loop control. Across multiple free-form language-guided autonomy coordination benchmarks, FLEET improves success over state of the art generative planners on two-agent teams across heterogeneous tasks. Ablations show that mixed integer linear programming (MILP) primarily improves temporal structure, while LLM-derived fitness is decisive for capability-coupled tasks; together they deliver the highest overall performance. We demonstrate the translation to real world challenges with hardware trials using a pair of quadruped robots with disjoint capabilities.

Most efforts to improve the reasoning capabilities of large language models (LLMs) involve either scaling the number of parameters and the size of training data, or scaling inference computation by letting models generate complex chains of thought. Motivated by interpretability studies showing that the crucial computation required for reasoning tasks is concentrated in a limited range of layers, we introduce Encode-Think-Decode (ETD), a method that enhances the reasoning capabilities of a base model by training it to iterate over a small subset of reasoning-relevant layers during the mid-training stage. ETD amplifies latent reasoning while preserving the original architecture, parameter count, hyperparameters, and training data composition. When iterating on the selected layers at inference time, ETD models yield substantial gains on 17 reasoning benchmarks, including +28.4% relative accuracy improvement on GSM8K and +36% on MATH with the OLMo-2 1B Base model. We also explore an adaptive depth strategy that adjusts the computation per input token. Our results show that recursive latent reasoning offers a simple and effective path to stronger LLM reasoning.

Surgical video datasets are essential for scene understanding, enabling procedural modeling and intra-operative support. However, these datasets are often heavily imbalanced, with rare actions and tools under-represented, which limits the robustness of downstream models. We address this challenge with $SurgiFlowVid$, a sparse and controllable video diffusion framework for generating surgical videos of under-represented classes. Our approach introduces a dual-prediction diffusion module that jointly denoises RGB frames and optical flow, providing temporal inductive biases to improve motion modeling from limited samples. In addition, a sparse visual encoder conditions the generation process on lightweight signals (e.g., sparse segmentation masks or RGB frames), enabling controllability without dense annotations. We validate our approach on three surgical datasets across tasks including action recognition, tool presence detection, and laparoscope motion prediction. Synthetic data generated by our method yields consistent gains of 10-20% over competitive baselines, establishing $SurgiFlowVid$ as a promising strategy to mitigate data imbalance and advance surgical video understanding methods.

Causal reasoning is fundamental for Large Language Models (LLMs) to understand genuine cause-and-effect relationships beyond pattern matching. Existing benchmarks suffer from critical limitations such as reliance on synthetic data and narrow domain coverage. We introduce a novel benchmark constructed from casually identified relationships extracted from top-tier economics and finance journals, drawing on rigorous methodologies including instrumental variables, difference-in-differences, and regression discontinuity designs. Our benchmark comprises 40,379 evaluation items covering five task types across domains such as health, environment, technology, law, and culture. Experimental results on eight state-of-the-art LLMs reveal substantial limitations, with the best model achieving only 57.6\% accuracy. Moreover, model scale does not consistently translate to superior performance, and even advanced reasoning models struggle with fundamental causal relationship identification. These findings underscore a critical gap between current LLM capabilities and demands of reliable causal reasoning in high-stakes applications.

Vision-Language Models (VLMs) have shown remarkable capabilities in spatial reasoning, yet they remain fundamentally limited to qualitative precision and lack the computational precision required for real-world robotics. Current approaches fail to leverage metric cues from depth sensors and camera calibration, instead reducing geometric problems to pattern recognition tasks that cannot deliver the centimeter-level accuracy essential for robotic manipulation. We present TIGeR (Tool-Integrated Geometric Reasoning), a novel framework that transforms VLMs from perceptual estimators to geometric computers by enabling them to generate and execute precise geometric computations through external tools. Rather than attempting to internalize complex geometric operations within neural networks, TIGeR empowers models to recognize geometric reasoning requirements, synthesize appropriate computational code, and invoke specialized libraries for exact calculations. To support this paradigm, we introduce TIGeR-300K, a comprehensive tool-invocation-oriented dataset covering point transformations, pose estimation, and spatial compatibility verification, complete with tool invocation sequences and intermediate computations. Through a two-stage training pipeline combining supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT) with our proposed hierarchical reward design, TIGeR achieves SOTA performance on geometric reasoning benchmarks while demonstrating centimeter-level precision in real-world robotic manipulation tasks.

LLMs are remarkable artifacts that have revolutionized a range of NLP and AI tasks. A significant contributor is their factual knowledge, which, to date, remains poorly understood, and is usually analyzed from biased samples. In this paper, we take a deep tour into the factual knowledge (or beliefs) of a frontier LLM, based on GPTKB v1.5 (Hu et al., 2025a), a recursively elicited set of 100 million beliefs of one of the strongest currently available frontier LLMs, GPT-4.1. We find that the models' factual knowledge differs quite significantly from established knowledge bases, and that its accuracy is significantly lower than indicated by previous benchmarks. We also find that inconsistency, ambiguity and hallucinations are major issues, shedding light on future research opportunities concerning factual LLM knowledge.

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the output level and do not constrain the reasoning process, leaving models exposed to implicit risks. In this paper, we propose SaFeR-VLM, a safety-aligned reinforcement learning framework that embeds safety directly into multimodal reasoning. The framework integrates four components: (I) QI-Safe-10K, a curated dataset emphasizing safety-critical and reasoning-sensitive cases; (II) safety-aware rollout, where unsafe generations undergo reflection and correction instead of being discarded; (III) structured reward modeling with multi-dimensional weighted criteria and explicit penalties for hallucinations and contradictions; and (IV) GRPO optimization, which reinforces both safe and corrected trajectories. This unified design shifts safety from a passive safeguard to an active driver of reasoning, enabling scalable and generalizable safety-aware reasoning. SaFeR-VLM further demonstrates robustness against both explicit and implicit risks, supporting dynamic and interpretable safety decisions beyond surface-level filtering. SaFeR-VLM-3B achieves average performance $70.13$ and $78.97$ on safety and helpfulness across six benchmarks, surpassing both same-scale and $>10\times$ larger models such as Skywork-R1V3-38B, Qwen2.5VL-72B, and GLM4.5V-106B. Remarkably, SaFeR-VLM-7B benefits from its increased scale to surpass GPT-5-mini and Gemini-2.5-Flash by \num{6.47} and \num{16.76} points respectively on safety metrics, achieving this improvement without any degradation in helpfulness performance. Our codes are available at https://github.com/HarveyYi/SaFeR-VLM.

Reinforcement Learning with Human Feedback (RLHF) has been the dominant approach for improving the reasoning capabilities of Large Language Models (LLMs). Recently, Reinforcement Learning with Verifiable Rewards (RLVR) has simplified this paradigm by replacing the reward and value models with rule-based verifiers. A prominent example is Group Relative Policy Optimization (GRPO). However, GRPO inherently suffers from a length bias, since the same advantage is uniformly assigned to all tokens of a response. As a result, longer responses distribute the reward over more tokens and thus contribute disproportionately to gradient updates. Several variants, such as DAPO and Dr. GRPO, modify the token-level aggregation of the loss, yet these methods remain heuristic and offer limited interpretability regarding their implicit token preferences. In this work, we explore the possibility of allowing the model to learn its own token preference during optimization. We unify existing frameworks under a single formulation and introduce a learnable parameter $λ$ that adaptively controls token-level weighting. We use $λ$-GRPO to denote our method, and we find that $λ$-GRPO achieves consistent improvements over vanilla GRPO and DAPO on multiple mathematical reasoning benchmarks. On Qwen2.5 models with 1.5B, 3B, and 7B parameters, $λ$-GRPO improves average accuracy by $+1.9\%$, $+1.0\%$, and $+1.7\%$ compared to GRPO, respectively. Importantly, these gains come without any modifications to the training data or additional computational cost, highlighting the effectiveness and practicality of learning token preferences.