AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving frontier. Like human cognitive development, agents are expected to acquire knowledge and skills through exploration and interaction with the environment. Despite advances, the community still lacks a unified, interactive reinforcement learning (RL) framework that can effectively train such agents from scratch -- without relying on supervised fine-tuning (SFT) -- across diverse and realistic environments. To bridge this gap, we introduce AgentGym-RL, a new framework to train LLM agents for multi-turn interactive decision-making through RL. The framework features a modular and decoupled architecture, ensuring high flexibility and extensibility. It encompasses a wide variety of real-world scenarios, and supports mainstream RL algorithms. Furthermore, we propose ScalingInter-RL, a training approach designed for exploration-exploitation balance and stable RL optimization. In early stages, it emphasizes exploitation by restricting the number of interactions, and gradually shifts towards exploration with larger horizons to encourage diverse problem-solving strategies. In this way, the agent develops more diverse behaviors and is less prone to collapse under long horizons. We perform extensive experiments to validate the stability and effectiveness of both the AgentGym-RL framework and the ScalingInter-RL approach. Our agents match or surpass commercial models on 27 tasks across diverse environments. We offer key insights and will open-source the complete AgentGym-RL framework -- including code and datasets -- to empower the research community in developing the next generation of intelligent agents.

TinySR: Pruning Diffusion for Real-World Image Super-Resolution

Real-world image super-resolution (Real-ISR) focuses on recovering high-quality images from low-resolution inputs that suffer from complex degradations like noise, blur, and compression. Recently, diffusion models (DMs) have shown great potential in this area by leveraging strong generative priors to restore fine details. However, their iterative denoising process incurs high computational overhead, posing challenges for real-time applications. Although one-step distillation methods, such as OSEDiff and TSD-SR, offer faster inference, they remain fundamentally constrained by their large, over-parameterized model architectures. In this work, we present TinySR, a compact yet effective diffusion model specifically designed for Real-ISR that achieves real-time performance while maintaining perceptual quality. We introduce a Dynamic Inter-block Activation and an Expansion-Corrosion Strategy to facilitate more effective decision-making in depth pruning. We achieve VAE compression through channel pruning, attention removal and lightweight SepConv. We eliminate time- and prompt-related modules and perform pre-caching techniques to further speed up the model. TinySR significantly reduces computational cost and model size, achieving up to 5.68x speedup and 83% parameter reduction compared to its teacher TSD-SR, while still providing high quality results.

Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

Effective tool use is essential for large language models (LLMs) to interact meaningfully with their environment. However, progress is limited by the lack of efficient reinforcement learning (RL) frameworks specifically designed for tool use, due to challenges in constructing stable training environments and designing verifiable reward mechanisms. To address this, we propose an automated environment construction pipeline, incorporating scenario decomposition, document generation, function integration, complexity scaling, and localized deployment. This enables the creation of high-quality training environments that provide detailed and measurable feedback without relying on external tools. Additionally, we introduce a verifiable reward mechanism that evaluates both the precision of tool use and the completeness of task execution. When combined with trajectory data collected from the constructed environments, this mechanism integrates seamlessly with standard RL algorithms to facilitate feedback-driven model training. Experiments on LLMs of varying scales demonstrate that our approach significantly enhances the models' tool-use performance without degrading their general capabilities, regardless of inference modes or training algorithms. Our analysis suggests that these gains result from improved context understanding and reasoning, driven by updates to the lower-layer MLP parameters in models.

Interpreting Fedspeak with Confidence: A LLM-Based Uncertainty-Aware Framework Guided by Monetary Policy Transmission Paths

"Fedspeak", the stylized and often nuanced language used by the U.S. Federal Reserve, encodes implicit policy signals and strategic stances. The Federal Open Market Committee strategically employs Fedspeak as a communication tool to shape market expectations and influence both domestic and global economic conditions. As such, automatically parsing and interpreting Fedspeak presents a high-impact challenge, with significant implications for financial forecasting, algorithmic trading, and data-driven policy analysis. In this paper, we propose an LLM-based, uncertainty-aware framework for deciphering Fedspeak and classifying its underlying monetary policy stance. Technically, to enrich the semantic and contextual representation of Fedspeak texts, we incorporate domain-specific reasoning grounded in the monetary policy transmission mechanism. We further introduce a dynamic uncertainty decoding module to assess the confidence of model predictions, thereby enhancing both classification accuracy and model reliability. Experimental results demonstrate that our framework achieves state-of-the-art performance on the policy stance analysis task. Moreover, statistical analysis reveals a significant positive correlation between perceptual uncertainty and model error rates, validating the effectiveness of perceptual uncertainty as a diagnostic signal.

Touch-Augmented Gaussian Splatting for Enhanced 3D Scene Reconstruction

This paper presents a multimodal framework that integrates touch signals (contact points and surface normals) into 3D Gaussian Splatting (3DGS). Our approach enhances scene reconstruction, particularly under challenging conditions like low lighting, limited camera viewpoints, and occlusions. Different from the visual-only method, the proposed approach incorporates spatially selective touch measurements to refine both the geometry and appearance of the 3D Gaussian representation. To guide the touch exploration, we introduce a two-stage sampling scheme that initially probes sparse regions and then concentrates on high-uncertainty boundaries identified from the reconstructed mesh. A geometric loss is proposed to ensure surface smoothness, resulting in improved geometry. Experimental results across diverse scenarios show consistent improvements in geometric accuracy. In the most challenging case with severe occlusion, the Chamfer Distance is reduced by over 15x, demonstrating the effectiveness of integrating touch cues into 3D Gaussian Splatting. Furthermore, our approach maintains a fully online pipeline, underscoring its feasibility in visually degraded environments.

LLMEval-3: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models

Existing evaluation of Large Language Models (LLMs) on static benchmarks is vulnerable to data contamination and leaderboard overfitting, critical issues that obscure true model capabilities. To address this, we introduce LLMEval-3, a framework for dynamic evaluation of LLMs. LLMEval-3 is built on a proprietary bank of 220k graduate-level questions, from which it dynamically samples unseen test sets for each evaluation run. Its automated pipeline ensures integrity via contamination-resistant data curation, a novel anti-cheating architecture, and a calibrated LLM-as-a-judge process achieving 90% agreement with human experts, complemented by a relative ranking system for fair comparison. An 20-month longitudinal study of nearly 50 leading models reveals a performance ceiling on knowledge memorization and exposes data contamination vulnerabilities undetectable by static benchmarks. The framework demonstrates exceptional robustness in ranking stability and consistency, providing strong empirical validation for the dynamic evaluation paradigm. LLMEval-3 offers a robust and credible methodology for assessing the true capabilities of LLMs beyond leaderboard scores, promoting the development of more trustworthy evaluation standards.

BokehDiff: Neural Lens Blur with One-Step Diffusion

We introduce BokehDiff, a novel lens blur rendering method that achieves physically accurate and visually appealing outcomes, with the help of generative diffusion prior. Previous methods are bounded by the accuracy of depth estimation, generating artifacts in depth discontinuities. Our method employs a physics-inspired self-attention module that aligns with the image formation process, incorporating depth-dependent circle of confusion constraint and self-occlusion effects. We adapt the diffusion model to the one-step inference scheme without introducing additional noise, and achieve results of high quality and fidelity. To address the lack of scalable paired data, we propose to synthesize photorealistic foregrounds with transparency with diffusion models, balancing authenticity and scene diversity.

IONext: Unlocking the Next Era of Inertial Odometry

Researchers have increasingly adopted Transformer-based models for inertial odometry. While Transformers excel at modeling long-range dependencies, their limited sensitivity to local, fine-grained motion variations and lack of inherent inductive biases often hinder localization accuracy and generalization. Recent studies have shown that incorporating large-kernel convolutions and Transformer-inspired architectural designs into CNN can effectively expand the receptive field, thereby improving global motion perception. Motivated by these insights, we propose a novel CNN-based module called the Dual-wing Adaptive Dynamic Mixer (DADM), which adaptively captures both global motion patterns and local, fine-grained motion features from dynamic inputs. This module dynamically generates selective weights based on the input, enabling efficient multi-scale feature aggregation. To further improve temporal modeling, we introduce the Spatio-Temporal Gating Unit (STGU), which selectively extracts representative and task-relevant motion features in the temporal domain. This unit addresses the limitations of temporal modeling observed in existing CNN approaches. Built upon DADM and STGU, we present a new CNN-based inertial odometry backbone, named Next Era of Inertial Odometry (IONext). Extensive experiments on six public datasets demonstrate that IONext consistently outperforms state-of-the-art (SOTA) Transformer- and CNN-based methods. For instance, on the RNIN dataset, IONext reduces the average ATE by 10% and the average RTE by 12% compared to the representative model iMOT.

PRISM: Distributed Inference for Foundation Models at Edge

Foundation models (FMs) have achieved remarkable success across a wide range of applications, from image classification to natural langurage processing, but pose significant challenges for deployment at edge. This has sparked growing interest in developing practical and efficient strategies for bringing foundation models to edge environments. In this work, we propose PRISM, a communication-efficient and compute-aware strategy for distributed Transformer inference on edge devices. Our method leverages a Segment Means representation to approximate intermediate output features, drastically reducing inter-device communication. Additionally, we restructure the self-attention mechanism to eliminate redundant computations caused by per-device Key/Value calculation in position-wise partitioning and design a partition-aware causal masking scheme tailored for autoregressive models. We evaluate PRISM on ViT, BERT, and GPT-2 across diverse datasets, namely CIFAR-10, CIFAR-100, ImageNet-1k, GLUE, and CBT. Our results demonstrate substantial reductions in communication overhead (up to 99.2% for BERT at compression rate CR = 128) and per-device computation (51.24% for BERT at the same setting), with only minor accuracy degradation. This method offers a scalable and practical solution for deploying foundation models in distributed resource-constrained environments.

Signal Prediction for Loss Mitigation in Tactile Internet: A Leader-Follower Game-Theoretic Approach

Tactile Internet (TI) requires achieving ultra-low latency and highly reliable packet delivery for haptic signals. In the presence of packet loss and delay, the signal prediction method provides a viable solution for recovering the missing signals. To this end, we introduce the Leader-Follower (LeFo) approach based on a cooperative Stackelberg game, which enables both users and robots to learn and predict actions. With accurate prediction, the teleoperation system can safely relax its strict delay requirements. Our method achieves high prediction accuracy, ranging from 80.62% to 95.03% for remote robot signals at the Human ($H$) side and from 70.44% to 89.77% for human operation signals at the remote Robot ($R$) side. We also establish an upper bound for maximum signal loss using Taylor Expansion, ensuring robustness.