arXiv subjects

Minghang Zhu

Publications and source records attributed to Minghang Zhu.

9 recordsLinked to original sources

arXiv2026

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

In this work, we present ZGCM-1, a fully open 7B dense foundation model trained from scratch with extreme data, system, and algorithmic efficiency. ZGCM-1 is founded on a core premise: compact models cannot passively memorize the open web, but can overcome parametric capacity limits by coupling deliberate internal thinking with active external tool use. To support this paradigm across a 256K context, we develop an end-to-end, high-efficiency open training recipe: Architecture & System Co-design: interleaved gated sliding-window and full attention, and a stable FP8 Muon optimizer; Progressive Curriculum & MDP Mid-Training: context scaling across 16K, 64K, and 256K, and the reformulation of interaction traces into Markov Decision Processes. Furthermore, we establish an AI-native R&D workflow where agent swarms autonomously manage cluster operations, data curation, and rapid diagnostic evaluation. Extensive evaluations show that ZGCM-1-7B is competitive across 7B model family on general benchmarks. On several challenging mathematical reasoning and agentic search suites, it remains competitive with frontier models orders of magnitude larger, such as Qwen3-235B-A22B and GLM-5.1. We also show that our pre-training design offers a ~4.2x efficiency improvement in 16K pre-training time-to-loss. Across the full development lifecycle, we distill eight actionable empirical findings-spanning architectural scaling, SFT quality pruning, long-context generalization, and agentic co-training dynamics. To facilitate community research, we open-source model weights from the pre-training, mid-training, and post-training stages, intermediate checkpoints, training code, per-stage data and data recipes, and W&B logs.

cs.AI↗

arXiv2026

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning

Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both training and inference. However, existing RMs struggle on knowledge-intensive and long-form tasks, where evaluating correctness requires grounding beyond the model's internal knowledge. This limitation hinders them from reliably discriminating subtle quality differences, especially when external evidence is necessary. To address this, we introduce OpenRM, a tool-augmented long-form reward model that systematically judges open-ended responses by invoking external tools to gather relevant evidence. We train OpenRM with Group Relative Policy Optimization (GRPO) on over 27K synthesized pairwise examples generated through a controllable data synthesis framework. The training objective jointly supervises intermediate tool usage and final outcome accuracy, incentivizing our reward model to learn effective evidence-based judgment strategies. Extensive experiments on three newly-collected datasets and two widely-used benchmarks demonstrate that OpenRM substantially outperforms existing reward modeling approaches. As a further step, we integrate OpenRM into both inference-time response selection and training-time data selection. This yields consistent gains in downstream LLM alignment tasks, highlighting the potential of tool-augmented reward models for scaling reliable long-form evaluation.

cs.CL↗

arXiv2026

DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents

Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewards improves these agents by optimizing them against checkable criteria that translate report quality into reward signals, but its efficiency depends on whether those criteria reliably capture the task scope and evidence needs. Most existing studies ask an LLM to generate rubrics for a given query, but when the model fails to infer the underlying information needs, the generated rubrics may be incomplete and reduce RL efficiency. To obtain more reliable query--rubric supervision, we introduce DeepRubric, a data construction framework that reverses this process: instead of inferring evaluation criteria for a given query, it first determines what an evidence-backed report should be evaluated on and then synthesizes aligned query--rubric pairs from those evaluation targets. Starting from a sampled seed topic, DeepRubric builds an evidence tree by recursively expanding evidence-backed sub-questions, whose leaves serve as atomic and verifiable evaluation targets. It then uses the evidence tree to synthesize the training query and rubrics, ensuring that the reward evaluates exactly the information requested by the query. Using DeepRubric, we construct 9K query--rubric supervision examples and train DeepRubric-8B with rubric-based GRPO, achieving comparable performance to prior open state-of-the-art deep research models across three benchmarks with roughly 13x fewer RL GPU-hours.

cs.CL↗

arXiv2026

LEADER: Learning Reliable Local-to-Global Correspondences for LiDAR Relocalization

LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-based regression methods offer efficient solutions by directly predicting global poses without the need for explicit map storage. However, these methods often struggle in challenging scenes due to their equal treatment of all predicted points, which is vulnerable to noise and outliers. In this paper, we propose LEADER, a robust LiDAR-based relocalization framework enhanced by a simple, yet effective geometric encoder. Specifically, a Robust Projection-based Geometric Encoder architecture which captures multi-scale geometric features is first presented to enhance descriptiveness in geometric representation. A Truncated Relative Reliability loss is then formulated to model point-wise ambiguity and mitigate the influence of unreliable predictions. Extensive experiments on the Oxford RobotCar and NCLT datasets demonstrate that LEADER outperforms state-of-the-art methods, achieving 24.1% and 73.9% relative reductions in position error over existing techniques, respectively. The source code is released on https://github.com/JiansW/LEADER.

cs.CV↗

arXiv2026

From Single Scan to Sequential Consistency: A New Paradigm for LIDAR Relocalization

LiDAR relocalization aims to estimate the global 6-DoF pose of a sensor in the environment. However, existing regression-based approaches are prone to dynamic or ambiguous scenarios, as they either solely rely on single-frame inference or neglect the spatio-temporal consistency across scans. In this paper, we propose TempLoc, a new LiDAR relocalization framework that enhances the robustness of localization by effectively modeling sequential consistency. Specifically, a Global Coordinate Estimation module is first introduced to predict point-wise global coordinates and associated uncertainties for each LiDAR scan. A Prior Coordinate Generation module is then presented to estimate inter-frame point correspondences by the attention mechanism. Lastly, an Uncertainty-Guided Coordinate Fusion module is deployed to integrate both predictions of point correspondence in an end-to-end fashion, yielding a more temporally consistent and accurate global 6-DoF pose. Experimental results on the NCLT and Oxford Robot-Car benchmarks show that our TempLoc outperforms stateof-the-art methods by a large margin, demonstrating the effectiveness of temporal-aware correspondence modeling in LiDAR relocalization. Our code will be released soon.

cs.CV↗

arXiv2025

Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems

The advancement of large language models (LLMs) has enabled the construction of multi-agent systems to solve complex tasks by dividing responsibilities among specialized agents, such as a planning agent for subgoal generation and a grounding agent for executing tool-use actions. Most existing methods typically fine-tune these agents independently, leading to capability gaps among them with poor coordination. To address this, we propose MOAT, a Multi-Agent Joint Alignment Tuning framework that improves agents collaboration through iterative alignment. MOAT alternates between two key stages: (1) Planning Agent Alignment, which optimizes the planning agent to generate subgoal sequences that better guide the grounding agent; and (2) Grounding Agent Improving, which fine-tunes the grounding agent using diverse subgoal-action pairs generated by the agent itself to enhance its generalization capablity. Theoretical analysis proves that MOAT ensures a non-decreasing and progressively convergent training process. Experiments across six benchmarks demonstrate that MOAT outperforms state-of-the-art baselines, achieving average improvements of 3.1% on held-in tasks and 4.4% on held-out tasks.

cs.CL↗

arXiv2025

Evolution without Large Models: Training Language Model with Task Principles

A common training approach for language models involves using a large-scale language model to expand a human-provided dataset, which is subsequently used for model training.This method significantly reduces training costs by eliminating the need for extensive human data annotation. However, it still faces challenges such as high carbon emissions during data augmentation and the risk of data leakage when we use closed-source LLMs. To address these issues, we propose a self-evolution method for language models. First, we introduce the Multi-level Principle Generation, which enables a large-scale model to summarize task-completion principles based on a small amount of task data. Then, we propose the Principle-based Instance Generation, in which a smaller-scale language model uses these task principles to generate a large amount of data. This data is then used for model training. Experimental results show that our proposed method significantly improves model performance compared to directly using a smaller-scale language model to generate data. Additionally, since we only use the large-scale language model to generate the task-completion principles, the carbon emissions associated with training the model are greatly reduced.

cs.CL↗

arXiv2024

Simulating Financial Market via Large Language Model based Agents

Most economic theories typically assume that financial market participants are fully rational individuals and use mathematical models to simulate human behavior in financial markets. However, human behavior is often not entirely rational and is challenging to predict accurately with mathematical models. In this paper, we propose \textbf{A}gent-based \textbf{S}imulated \textbf{F}inancial \textbf{M}arket (ASFM), which first constructs a simulated stock market with a real order matching system. Then, we propose a large language model based agent as the stock trader, which contains the profile, observation, and tool-learning based action module. The trading agent can comprehensively understand current market dynamics and financial policy information, and make decisions that align with their trading strategy. In the experiments, we first verify that the reactions of our ASFM are consistent with the real stock market in two controllable scenarios. In addition, we also conduct experiments in two popular economics research directions, and we find that conclusions drawn in our \model align with the preliminary findings in economics research. Based on these observations, we believe our proposed ASFM provides a new paradigm for economic research.

cs.CL↗

arXiv2023

Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum

Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extending the capability of LLMs. Although some works employ open-source LLMs for the tool learning task, most of them are trained in a controlled environment in which LLMs only learn to execute the human-provided tools. However, selecting proper tools from the large toolset is also a crucial ability for the tool learning model to be applied in real-world applications. Existing methods usually directly employ self-instruction methods to train the model, which ignores differences in tool complexity. In this paper, we propose the Confucius, a novel tool learning framework to train LLM to use complicated tools in real-world scenarios, which contains two main phases: (1) We first propose a multi-stage learning method to teach the LLM to use various tools from an easy-to-difficult curriculum; (2) thenceforth, we propose the Iterative Self-instruct from Introspective Feedback (ISIF) to dynamically construct the dataset to improve the ability to use the complicated tool. Extensive experiments conducted on both controlled and real-world settings demonstrate the superiority of our tool learning framework in the real-world application scenarios compared to both tuning-free (e.g. ChatGPT, Claude) and tuning-based baselines (e.g. GPT4Tools).

cs.AI↗