We release Intern-S1-MO, a hierarchical math agent built by SFT and agent RL to solving IMO-level math problems
摘要
Large Reasoning Models (LRMs) have expanded the mathematical reasoning frontier through Chain-of-Thought (CoT) techniques and Reinforcement Learning with Verifiable Rewards (RLVR). However, the performance of LRMs is heavily dependent on the extended reasoning context length. For solving ultra-hard problems like those in the International Mathematical Olympiad (IMO), the required reasoning complexity surpasses the space that an LRM can explore in a single round. Previous works attempt to extend the reasoning context of LRMs but remain prompt-based and built upon proprietary models, lacking systematic structures and training pipelines. Therefore, this paper introduces Intern-S1-MO, a long-horizon math agent that conducts multi-round hierarchical reasoning, composed of an LRM-based multi-agent system including reasoning, summary, and verification. By maintaining a compact memory in the form of lemmas, Intern-S1-MO can more freely explore the lemma-rich reasoning spaces in multiple reasoning stages, thereby breaking through the context constraints for IMO-level math problems. Furthermore, we propose OREAL-H, an RL framework for training the LRM using the online explored trajectories to simultaneously bootstrap the reasoning ability of the LRM. Experiments show that Intern-S1-MO obtains 26 out of 35 points on the non-geometry problems of IMO2025, matching the performance of silver medalists. It also surpasses the current advanced LRMs on inference benchmarks such as HMMT2025 and AIME2025. In addition, it officially participates in CMO2025 and achieves a score of 102/126 under the judgment of human experts, reaching the gold medal level.
推理强化学习与后训练智能体与工具Large Language ModelReinforcement LearningMathmatical ReasoningOpenReview
An open data synthesis framework for building competitive mobile agents.
摘要
Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achieving a marked performance leap, e.g., nearly 70\% success on AndroidWorld.
However, these systems keep their training data closed and remain opaque about their task and trajectory synthesis recipes.
We present **OpenMobile**, an open-source framework that synthesizes high-quality task instructions and agent trajectories, with two key components:
(1) The first is a scalable task synthesis pipeline that constructs a global environment memory from exploration, then leverages it to generate diverse and grounded instructions.
and (2) a policy-switching strategy for trajectory rollout. By alternating between learner and expert models, it captures essential error-recovery data often missing in standard imitation learning.
Agents trained on our data achieve competitive results across three dynamic mobile agent benchmarks: notably, our fine-tuned Qwen2.5-VL and Qwen3-VL reach 51.7\% and **64.7\% on AndroidWorld**, far surpassing existing open-data approaches.
Furthermore, we conduct transparent analyses on the overlap between our synthetic instructions and benchmark test sets, and verify that performance gains stem from broad functionality coverage rather than benchmark overfitting.
We release data and code at [OpenMobile](https://njucckevin.github.io/openmobile/) to bridge the data gap and facilitate broader mobile agent research.
智能体与工具检索与知识多模态Mobile AgentGUI AgentVision Language ModelLarge Language ModelOpenReview
作者位次 #7/8ICLR 2026Poster· Applications / Language, Speech and Dialog
The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner
As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with frequent tool calls, the traditional generation-length-based definition breaks down: tool latency decouples inference t...
Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs), yet datasets are often treated as isolated artifacts, overlooking the systemic connections that underlie their evolution. To disentangle these complex relationships, we introduce the concept of da...
We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from...
Training large language models (LLMs) at 4-bit precision offers substantial efficiency gains but remains challenging due to the limited dynamic range and coarse numerical resolution. Existing 4-bit training pipelines typically rely on max-scaling, which is ill-suited for heavy-tailed LLM tensor d...