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。
EverMind AI
Raven is an open-source multi-agent ecosystem that autonomously builds and evolves modular harnesses, enabling cross-domain collaboration and expanding reliable task coverage through composable agent units.
50 篇论文 · 按点赞排序
Ke Yang, Chenglong Wang, Michel Galley +4 authors
StudentSim trains personalized student simulators from sparse data to mirror learner responses and adapt to tutor guidance, outperforming existing models across chess, writing, and math.
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16 authors
HarnessDev evaluates agents by measuring their ability to build and iteratively improve execution infrastructure rather than final task outputs, revealing that self-built harnesses vary widely in capability and efficiency and transfer poorly across models.
Yanlin Li, Mingyang Hao, Shengqiong Wu +3 authors
Omni-IO Skills is a plug-and-play harness that enables general agents to coordinate multimodal workflows across diverse artifacts via hierarchical skills, dependency-aware orchestration, and a persistent asset registry.
Xiyuan Yang, Sheikh Sarwar, Jingru Cheng +8 authors
World Model RL replaces costly environment execution with a learned world model and applies debiasing and denoising to accelerate post-training of autonomous research agents.
NeoHorse Team, Guoliang Cao, Guohao Dai +34 authors
NeoHorse-1 uses agentic post-training with intelligent routing, structured feedback loops, and curriculum-based distillation to improve model capabilities across agent benchmarks.
Jianlyu Chen, Yuyang Hu, Hongjin Qian +8 authors
DisCo is a research agent that distills operational knowledge into reusable skills, significantly improving autonomous ML research performance across benchmarks.
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +18 authors
ASPIRE introduces a benchmark for self-evolving LLM agents from vague natural-language goals, revealing challenges in goal interpretation, data selection, and stable weight-level improvement.
Dingjie Song, Hanrong Zhang, Dawei Liu +10 authors
Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, IDEs, terminals, and writing environments, and the decisions that make it auditable are rarely preserved. We present Dr. Claw, an open-source workspace that wraps existing coding-agent executors in a controllable and auditable human-in-the-loop workflow rather than introducing another autonomous agent. Persistent state objects, a reusable skill library, and multi-executor coordination link human decisions to AI execution, turning planning, execution, and writing into one traceable, recoverable loop. We demonstrate Dr. Claw through an interactive three-view scenario and a failure-recovery walkthrough, and evaluate it against a bare command-line agent sharing the same backend executor, so the comparison contrasts the whole orchestration layer (task graph, state objects, and skill library) with the agent it wraps. Holding the executor fixed, Dr. Claw scores higher on research completeness while persisting an auditable, recoverable process trail. Demo access: repository https://github.com/OpenLAIR/dr-claw, released under AGPL-3.0 with GPL-3.0 upstream components.
Honglin Guo, Tao Gui, Yicheng Chen +140 authors
Atria Dawn Preview is a foundation agentic language model trained through verified tool interactions that achieves strong benchmark results and demonstrates a shift toward human-AI project-level collaboration in scientific research.
Zheyuan Zhang, Alvin Zhang, Daniel Khashabi +1 authors
Composing complementary continual learning mechanisms substantially improves long-horizon memorization in language models by combining data, function, and weight anchors with merged low-rank updates.
Xin Zhou, Zongchuang Zhao, Zhibo Yang +13 authors
Qwen-Drive-1.0 is a vision-language foundation model for autonomous driving that unifies 3D perception, visual question answering, and motion planning via shared representations and staged training.
Tong Zheng, Xidong Wu, Zheng Zhang +14 authors
Dream-RSI enables scalable recursive self-improvement by using historical discovery replay to evaluate exploration policies offline, reducing costly online evaluations.
Yuntai Bao, Qinfeng Li, Guoqing Jiang +5 authors
On-policy distillation of reinforcement learning improves reasoning across model scales with predictable scaling laws, showing that smaller teachers can outperform larger ones at matched scores and that students often exceed their teachers.
Siran Peng, Tianshuo Zhang, Tianyu Fu +8 authors
VisionHOPE introduces a self-modifying visual backbone where memory and learning co-evolve through coupled memories and stability-controlled updates, achieving strong results across vision tasks.
Xingxuan Zhang, Gang Ren, Hao Yuan +57 authors
LimiX-2 is a scaled tabular foundation model using contextual mechanism networks and context-conditional masked modeling to learn joint data structures, improving predictions and causal skeleton recovery.
Jiyan He, Guang Liang, Hao Liu +19 authors
ZGCM-1 is a 7B open foundation model that combines internal reasoning with external tool use, trained via efficient architecture-system co-design, progressive long-context scaling, and autonomous agent workflows to achieve strong reasoning and efficiency.
Jintao Zhang, Kai Jiang, Jintao Chen +32 authors
Vidu S2 introduces real-time interactive avatar and video editing models that support high-resolution spatial video generation and dynamic reference updates.
Ziyang Zhang, Yubin Jing, Yuanhao Zeng +3 authors
Active Taskless Distillation enables language models to acquire task capabilities from a teacher using only single unrelated words, without direct task examples or model access.
Yuntian Deng, Pengyu Nie, Stuart Shieber
Compile by training converts natural-language specifications into reusable neural functions by distilling teacher-generated examples into small adapters, enabling efficient deployment without remote model dependencies.
Siwei Wu, Jincheng Ren, Yizhi Li +11 authors
ModularRSI improves agent harnesses through benchmark-independent, contrastive, modular evolution that isolates recurring deficiencies and evolves functional components independently.
Hao Liang, Qihan Lin, Meiyi Qiang +5 authors
OmniEdu is a family of instruction-tuned educational foundation models that improve K-12 problem solving, curriculum understanding, and tutoring through capability-balanced training data.
DeepSeek-AI, Anyi Xu, B. Li +589 authors
DeepSeek-V4.1-Flash is a multimodal MoE model using a CED architecture and aggressive KV cache compression to lower compute, storage, and bandwidth costs for long-context agent workloads.
Peng Xia, Rujun Han, Zifeng Wang +11 authors
Regularized recursive self-improvement of agent harnesses improves out-of-distribution performance by constraining edit proposals and selections to favor reusable mechanisms over benchmark-specific memorization.
Koutian Wu, Junjie Zhou, Ergan Shang +4 authors
Benchmark Radar is a searchable living database and discovery engine for AI evaluation benchmarks that aggregates sources, score histories, and evidence to support benchmark selection and comparison.
Haoyu Zhao, Zihao Zhang, Xudong Wang +4 authors
MaLiang-Harness defines the Program-to-Visual gap and uses persistent executable generation, traceable editing, and revision-aware verification to improve multimodal language model-driven visual creation.
Hao Liang, Mingrui Chen, Hengyi Feng +2 authors
DataFlex-RL evaluates reinforcement learning data policies and finds that uniform sampling matches or exceeds adaptive rollout selection, reweighting, and domain mixing across math, logic, and science benchmarks.
Ruibin Yuan, Jiahao Pan, Junyan Jiang +32 authors
YuE2 unifies symbolic and audio music generation via symbolic planning, producing readable scores and full-song audio with state-of-the-art quality and agentic editing capabilities.
NCP Team, Jiaqi Cao, Chiyu Chen +25 authors
NCP-ArchPreview is a large latent-space language model that jointly trains next-token and next-concept prediction to improve pretraining efficiency and downstream performance.
Xin Li, Hao Jiang, Xin Gao +6 authors
Multi-teacher on-policy distillation merges specialist language models but suffers from unbalanced feedback across domains, which domain-normalized rescaling fixes to recover lost skills.
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