Explore · 每周精选
发现最受关注的研究论文,追踪研究趋势,订阅感兴趣的期刊与关键词。
686 篇论文 · 按点赞排序
Yuan Liang, Ruobin Zhong, Haoming Xu +46 authors
SkillNet introduces an open infrastructure for systematically accumulating and transferring AI skills through a unified ontology, significantly improving agent performance across multiple domains.
Jiayu Liu, Qihan Lin, Cheng Qian +8 authors
PlanBench-XL evaluates large language model agents' ability to plan and adapt in complex tool-rich environments with limited visibility and dynamic disruptions.
Eunbi Choi, Kibong Choi, Seokhee Hong +62 authors
K-EXAONE is a multilingual language model with a Mixture-of-Experts architecture that achieves competitive performance on various benchmarks while supporting multiple languages and long-context windows.
Xin Xu, Clive Bai, Kai Yang +7 authors
Composition-RL improves reasoning capabilities by automatically composing multiple problems into new verifiable questions for reinforcement learning training.
Xianjin Wu, Dingkang Liang, Tianrui Feng +5 authors
A video diffusion model is repurposed as a latent world simulator to enhance multimodal large language models with implicit 3D structural priors and physical laws through spatiotemporal feature extraction and semantic integration.
Zhongxing Xu, Zhonghua Wang, Zhe Qian +10 authors
Latent Entropy-Aware Decoding (LEAD) enhances multimodal large reasoning models by using entropy-aware reasoning mode switching and prior-guided visual anchor injection to reduce hallucinations.
Haoyu Zhao, Xingyue Zhao, Siteng Huang +3 authors
A multi-modal 4D world model generates synchronized RGB, depth, and optical flow data from single RGB-D images and language instructions, enabling efficient robotic manipulation through unified diffusion processes and inverse dynamics policy learning.
Senqiao Yang, Chengyao Wang, Yuxin Chen +13 authors
VLAct improves vision-language-action model performance by pre-training on diverse robot data with preserved vision-language priors and shared action semantics, achieving strong results across simulations and unseen embodiments with limited compute.
Shaoqiu Zhang, Maoquan Wang, Yuling Shi +5 authors
FastContext separates repository exploration from code solving in LLM agents using specialized exploration models that reduce token consumption and improve resolution rates.
Xinyu Geng, Xuanhua He, Sixiang Chen +7 authors
Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward reinforcement learning provides weak supervision for long-horizon interactions. We present DeepSearch-Evolve, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools. DeepSearch-World contains 420K multi-hop QA tasks constructed from entity-level random walks and supports key agentic cognitive behaviors useful for self-evolving, including progress verification, grounded reflection, and failure recovery. DeepSearch-Evolve iteratively performs trajectory generation, filtering, data mixing, and fine-tuning to train stronger agents. Without distillation from more capable models, DeepSearch-World-9B achieves competitive performance compared with open-source agents, reaching 31.2% on BrowseComp, 61.5% on GAIA, and 93.4% on HotpotQA, showing that verifiable environments enable scalable self-evolution for long-horizon web agents. We will release the environment, 420K training pool, validation set, model, and code to facilitate future research on self-improving deep search agents.
Jiacheng Chen, Xinyu Zhang, Shunkai Zhang +20 authors
MaxProof is a test-time scaling framework that enhances mathematical proof generation by combining multiple proof-oriented capabilities and using population-level search with tournament selection to achieve competitive performance on high-level mathematical competitions.
Jiaxing Li, Kai Zou, Cindy Zhou +7 authors
Joint distillation aligns initialization and refinement distributions to improve coverage and diversity in autoregressive video generation.
Junjie Li, Xinrui Guo, Yuhao Wu +3 authors
Large language models struggle with maintaining narrative consistency over long-form storytelling, exhibiting predictable patterns of contradictions that this benchmark identifies and categorizes.
Junliang Ye, Kenkun Liu, Guocun Wang +12 authors
Hunyuan3D-Buffalo 1.0 unifies 3D understanding, generation, editing, and part generation via a multimodal architecture trained on a large-scale 3D corpus, achieving leading benchmark results.
Qing Zong, Yue Guo, Mengxin Yang +2 authors
EvolvingWorld is a framework and benchmark that models interactive literary worlds as long-horizon co-evolution processes using coupled character and world modules with LLM-based state maintenance and evaluation.
Minki Kang, Shizhe Diao, Ryo Hachiuma +4 authors
Agents using vision-language models with extended reasoning face challenges in tool utilization, which are addressed through AXPO, a method that improves performance by optimizing thinking prefixes and tool call resampling.
Hongtao Wu, Boyun Zheng, Dingjie Song +5 authors
Medical AI Scientist represents the first autonomous research framework designed for clinical applications, enabling evidence-based hypothesis generation and manuscript drafting through clinician-engineer collaboration across three research modes.
AlayaWorld Team, Kaipeng Zhang, Chuanhao Li +14 authors
AlayaWorld is an open-source framework for creating interactive generative worlds that enables real-time user interaction and supports diverse actions within a modular architecture.
Hangrui Xu, Jiarui Wang, Yang Yang +5 authors
DART-SD improves multi-turn tool-calling agents by modeling execution as a diamond-topology graph, identifying critical failure points, and applying localized self-distillation to preserve valid reasoning while correcting errors.
Yuhang Wang, Yuling Shi, Mo Yang +7 authors
SWE-Pruner is a self-adaptive context pruning framework for coding agents that uses task-aware pruning to reduce token usage while maintaining performance.
Taofeng Xue, Chong Peng, Mianqiu Huang +13 authors
EvoCUA introduces an evolutionary approach to computer-use agents that combines autonomous task generation with policy optimization to achieve superior performance in complex, long-horizon tasks.
Zixun Huang, Kishan Panaganti, Haitao Mi +1 authors
FlowBalance improves reasoning models via verifier-calibrated self-guidance using trajectory-level score reweighting and profile-based trajectory balance.
Zhiyuan Hu, Yunhai Hu, Juncheng Liu +9 authors
Multi-Agent Test-Time Reinforcement Learning (MATTRL) enhances multi-agent reasoning through structured textual experience injection and consensus-based decision making at inference time.
Anton Razzhigaev, Andrei Gritsaev, Andrei Kaznacheev +3 authors
We present Ouroboros, a self-developing agent harness whose tools, prompts, context assembly, and core implementation improve through reviewed commits that become the runtime for later work. Core evolution proceeds in two modes. In recursive free evolution, improvement is itself a task, and completing one evolution cycle can schedule the next. In experience-driven core evolution, ordinary work and social interaction expose bugs, rough edges, and inefficient context construction that lead to reviewed structural changes. On Terminal-Bench 2.1, an Opus 5 run scores 86.74%, the best result reported on the benchmark. On OSWorld-Verified, an Opus 5 run reaches 90.69%, exceeding the best previously reported score. A five-rollout CL-Bench campaign achieves a normalized reward of 0.2301, setting a new state of the art. Hope is the longest-running publicly documented Ouroboros deployment. It is a 161-day living agent experiment in free evolution under governed human communication across seven surfaces. Human interaction surfaces faults and generates proposals, but the agent decides which changes to pursue. Because a self-developing agent may rewrite its own code and select new model APIs, operational safety becomes a primary design problem: guardrails must remain authoritative under evolutionary and public social pressure. Benchmark campaigns use frozen system snapshots, while Hope continues live evolution on a separate lineage.
Zhen Li, Zian Meng, Shuwei Shi +5 authors
WildWorld is a large-scale dataset for action-conditioned world modeling that provides explicit state annotations from a photorealistic game, enabling better understanding of latent-state dynamics and long-horizon consistency.
Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov +1 authors
A large-scale dataset of software engineering tasks spanning multiple programming languages and repositories was created using an automated pipeline that generates executable environments and filters unreliable instances through LLM validation.
Fangfu Liu, Diankun Wu, Jiawei Chi +7 authors
Spatial-TTT enables streaming visual-based spatial intelligence through test-time training that adapts parameters to capture spatial evidence over long video sequences using hybrid architecture and 3D spatiotemporal convolution.
Nimrod Shabtay, Moshe Kimhi, Artem Spector +5 authors
AwaRes is a spatial-on-demand framework for vision-language models that dynamically retrieves high-resolution image segments based on query needs, using tool-calling and multi-turn reinforcement learning with composite rewards.
Zixuan Fu, Bingxiang He, Yuxin Zuo +10 authors
On-policy distillation improves over hundreds of steps from a single query by rapidly covering teacher states, yet student alignment remains slow, indicating the method is algorithm-starved rather than data-starved.
Chenkai Pan, Xinglong Xu, Yuhang Xu +6 authors
Training data can be structured as source code and evaluated through unit testing, enabling systematic debugging and improvement of language models' domain-specific capabilities.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号