ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning

Large Language Models (LLMs) equipped with external tools have demonstrated enhanced performance on complex reasoning tasks. The widespread adoption of this tool-augmented reasoning is hindered by the scarcity of domain-specific tools. For instance, in domains such as physics question answering, suitable and specialized tools are often missing. Recent work has explored automating tool creation by extracting reusable functions from Chain-of-Thought (CoT) reasoning traces; however, these approaches face a critical scalability bottleneck. As the number of generated tools grows, storing them in an unstructured collection leads to significant retrieval challenges, including an expanding search space and ambiguity between function-related tools. To address this, we propose a systematic approach to automatically refactor an unstructured collection of tools into a structured tool library. Our system first generates discrete, task-specific tools and clusters them into semantically coherent topics. Within each cluster, we introduce a multi-agent framework to consolidate scattered functionalities: a code agent refactors code to extract shared logic and creates versatile, aggregated tools, while a reviewing agent ensures that these aggregated tools maintain the complete functional capabilities of the original set. This process transforms numerous question-specific tools into a smaller set of powerful, aggregated tools without loss of functionality. Experimental results demonstrate that our approach significantly improves tool retrieval accuracy and overall reasoning performance across multiple reasoning tasks. Furthermore, our method shows enhanced scalability compared with baselines as the number of question-specific increases.

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Fine-grained visual reasoning remains a core challenge for multimodal large language models (MLLMs). The recently introduced ReasonMap highlights this gap by showing that even advanced MLLMs struggle with spatial reasoning in structured and information-rich settings such as transit maps, a task of clear practical and scientific importance. However, standard reinforcement learning (RL) on such tasks is impeded by sparse rewards and unstable optimization. To address this, we first construct ReasonMap-Plus, an extended dataset that introduces dense reward signals through Visual Question Answering (VQA) tasks, enabling effective cold-start training of fine-grained visual understanding skills. Next, we propose RewardMap, a multi-stage RL framework designed to improve both visual understanding and reasoning capabilities of MLLMs. RewardMap incorporates two key designs. First, we introduce a difficulty-aware reward design that incorporates detail rewards, directly tackling the sparse rewards while providing richer supervision. Second, we propose a multi-stage RL scheme that bootstraps training from simple perception to complex reasoning tasks, offering a more effective cold-start strategy than conventional Supervised Fine-Tuning (SFT). Experiments on ReasonMap and ReasonMap-Plus demonstrate that each component of RewardMap contributes to consistent performance gains, while their combination yields the best results. Moreover, models trained with RewardMap achieve an average improvement of 3.47% across 6 benchmarks spanning spatial reasoning, fine-grained visual reasoning, and general tasks beyond transit maps, underscoring enhanced visual understanding and reasoning capabilities.

LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

The emergence of long-context language models with context windows extending to millions of tokens has created new opportunities for sophisticated code understanding and software development evaluation. We propose LoCoBench, a comprehensive benchmark specifically designed to evaluate long-context LLMs in realistic, complex software development scenarios. Unlike existing code evaluation benchmarks that focus on single-function completion or short-context tasks, LoCoBench addresses the critical evaluation gap for long-context capabilities that require understanding entire codebases, reasoning across multiple files, and maintaining architectural consistency across large-scale software systems. Our benchmark provides 8,000 evaluation scenarios systematically generated across 10 programming languages, with context lengths spanning 10K to 1M tokens, a 100x variation that enables precise assessment of long-context performance degradation in realistic software development settings. LoCoBench introduces 8 task categories that capture essential long-context capabilities: architectural understanding, cross-file refactoring, multi-session development, bug investigation, feature implementation, code comprehension, integration testing, and security analysis. Through a 5-phase pipeline, we create diverse, high-quality scenarios that challenge LLMs to reason about complex codebases at unprecedented scale. We introduce a comprehensive evaluation framework with 17 metrics across 4 dimensions, including 8 new evaluation metrics, combined in a LoCoBench Score (LCBS). Our evaluation of state-of-the-art long-context models reveals substantial performance gaps, demonstrating that long-context understanding in complex software development represents a significant unsolved challenge that demands more attention. LoCoBench is released at: https://github.com/SalesforceAIResearch/LoCoBench.

On-Device Diffusion Transformer Policy for Efficient Robot Manipulation

Diffusion Policies have significantly advanced robotic manipulation tasks via imitation learning, but their application on resource-constrained mobile platforms remains challenging due to computational inefficiency and extensive memory footprint. In this paper, we propose LightDP, a novel framework specifically designed to accelerate Diffusion Policies for real-time deployment on mobile devices. LightDP addresses the computational bottleneck through two core strategies: network compression of the denoising modules and reduction of the required sampling steps. We first conduct an extensive computational analysis on existing Diffusion Policy architectures, identifying the denoising network as the primary contributor to latency. To overcome performance degradation typically associated with conventional pruning methods, we introduce a unified pruning and retraining pipeline, optimizing the model's post-pruning recoverability explicitly. Furthermore, we combine pruning techniques with consistency distillation to effectively reduce sampling steps while maintaining action prediction accuracy. Experimental evaluations on the standard datasets, \ie, PushT, Robomimic, CALVIN, and LIBERO, demonstrate that LightDP achieves real-time action prediction on mobile devices with competitive performance, marking an important step toward practical deployment of diffusion-based policies in resource-limited environments. Extensive real-world experiments also show the proposed LightDP can achieve performance comparable to state-of-the-art Diffusion Policies.

UserBench: An Interactive Gym Environment for User-Centric Agents

Large Language Models (LLMs)-based agents have made impressive progress in reasoning and tool use, enabling them to solve complex tasks. However, their ability to proactively collaborate with users, especially when goals are vague, evolving, or indirectly expressed, remains underexplored. To address this gap, we introduce UserBench, a user-centric benchmark designed to evaluate agents in multi-turn, preference-driven interactions. UserBench features simulated users who start with underspecified goals and reveal preferences incrementally, requiring agents to proactively clarify intent and make grounded decisions with tools. Our evaluation of leading open- and closed-source LLMs reveals a significant disconnect between task completion and user alignment. For instance, models provide answers that fully align with all user intents only 20% of the time on average, and even the most advanced models uncover fewer than 30% of all user preferences through active interaction. These results highlight the challenges of building agents that are not just capable task executors, but true collaborative partners. UserBench offers an interactive environment to measure and advance this critical capability.

When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios

Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input. While this ability significantly enhances MLLM capabilities, it introduces substantial computational challenges, primarily due to the quadratic complexity of self-attention mechanisms with numerous input tokens. To mitigate these bottlenecks, token compression has emerged as an auspicious and critical approach, efficiently reducing the number of tokens during both training and inference. In this paper, we present the first systematic survey and synthesis of the burgeoning field of multimodal long context token compression. Recognizing that effective compression strategies are deeply tied to the unique characteristics and redundancies of each modality, we categorize existing approaches by their primary data focus, enabling researchers to quickly access and learn methods tailored to their specific area of interest: (1) image-centric compression, which addresses spatial redundancy in visual data; (2) video-centric compression, which tackles spatio-temporal redundancy in dynamic sequences; and (3) audio-centric compression, which handles temporal and spectral redundancy in acoustic signals. Beyond this modality-driven categorization, we further dissect methods based on their underlying mechanisms, including transformation-based, similarity-based, attention-based, and query-based approaches. By providing a comprehensive and structured overview, this survey aims to consolidate current progress, identify key challenges, and inspire future research directions in this rapidly evolving domain. We also maintain a public repository to continuously track and update the latest advances in this promising area.

See the Forest and the Trees: A Synergistic Reasoning Framework for Knowledge-Based Visual Question Answering

Multimodal Large Language Models (MLLMs) have pushed the frontiers of Knowledge-Based Visual Question Answering (KBVQA), yet their reasoning is fundamentally bottlenecked by a reliance on uni-dimensional evidence. This "seeing only the trees, but not the forest" approach prevents robust, multi-faceted understanding. Inspired by the principle of seeing both the forest and trees, we propose Synergos-VQA, a novel synergistic reasoning framework. At its core, Synergos-VQA concurrently generates and fuses three complementary evidence streams at inference time: (1) Holistic Evidence to perceive the entire scene (the "forest"), (2) Structural Evidence from a prototype-driven module to identify key objects (the "trees"), and (3) Causal Evidence from a counterfactual probe to ensure the reasoning is robustly grounded. By synergistically fusing this multi-faceted evidence, our framework achieves a more comprehensive and reliable reasoning process. Extensive experiments show that Synergos-VQA decisively establishes a new state-of-the-art on three challenging benchmarks, including OK-VQA and A-OKVQA. Furthermore, our approach demonstrates strong plug-and-play capabilities, significantly boosting various open-source MLLMs and proving that superior methodological design can outperform sheer model scale.

FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning

Federated learning aims at training models collaboratively across participants while protecting privacy. However, one major challenge for this paradigm is the data heterogeneity issue, where biased data preferences across multiple clients, harming the model's convergence and performance. In this paper, we first introduce powerful diffusion models into the federated learning paradigm and show that diffusion representations are effective steers during federated training. To explore the possibility of using diffusion representations in handling data heterogeneity, we propose a novel diffusion-inspired Federated paradigm with Diffusion Representation Collaboration, termed FedDifRC, leveraging meaningful guidance of diffusion models to mitigate data heterogeneity. The key idea is to construct text-driven diffusion contrasting and noise-driven diffusion regularization, aiming to provide abundant class-related semantic information and consistent convergence signals. On the one hand, we exploit the conditional feedback from the diffusion model for different text prompts to build a text-driven contrastive learning strategy. On the other hand, we introduce a noise-driven consistency regularization to align local instances with diffusion denoising representations, constraining the optimization region in the feature space. In addition, FedDifRC can be extended to a self-supervised scheme without relying on any labeled data. We also provide a theoretical analysis for FedDifRC to ensure convergence under non-convex objectives. The experiments on different scenarios validate the effectiveness of FedDifRC and the efficiency of crucial components.

FedSC: Federated Learning with Semantic-Aware Collaboration

Federated learning (FL) aims to train models collaboratively across clients without sharing data for privacy-preserving. However, one major challenge is the data heterogeneity issue, which refers to the biased labeling preferences at multiple clients. A number of existing FL methods attempt to tackle data heterogeneity locally (e.g., regularizing local models) or globally (e.g., fine-tuning global model), often neglecting inherent semantic information contained in each client. To explore the possibility of using intra-client semantically meaningful knowledge in handling data heterogeneity, in this paper, we propose Federated Learning with Semantic-Aware Collaboration (FedSC) to capture client-specific and class-relevant knowledge across heterogeneous clients. The core idea of FedSC is to construct relational prototypes and consistent prototypes at semantic-level, aiming to provide fruitful class underlying knowledge and stable convergence signals in a prototype-wise collaborative way. On the one hand, FedSC introduces an inter-contrastive learning strategy to bring instance-level embeddings closer to relational prototypes with the same semantics and away from distinct classes. On the other hand, FedSC devises consistent prototypes via a discrepancy aggregation manner, as a regularization penalty to constrain the optimization region of the local model. Moreover, a theoretical analysis for FedSC is provided to ensure a convergence guarantee. Experimental results on various challenging scenarios demonstrate the effectiveness of FedSC and the efficiency of crucial components.

Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement Learning

Offline reinforcement learning (RL) heavily relies on the coverage of pre-collected data over the target policy's distribution. Existing studies aim to improve data-policy coverage to mitigate distributional shifts, but overlook security risks from insufficient coverage, and the single-step analysis is not consistent with the multi-step decision-making nature of offline RL. To address this, we introduce the sequence-level concentrability coefficient to quantify coverage, and reveal its exponential amplification on the upper bound of estimation errors through theoretical analysis. Building on this, we propose the Collapsing Sequence-Level Data-Policy Coverage (CSDPC) poisoning attack. Considering the continuous nature of offline RL data, we convert state-action pairs into decision units, and extract representative decision patterns that capture multi-step behavior. We identify rare patterns likely to cause insufficient coverage, and poison them to reduce coverage and exacerbate distributional shifts. Experiments show that poisoning just 1% of the dataset can degrade agent performance by 90%. This finding provides new perspectives for analyzing and safeguarding the security of offline RL.