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。
Björn Engdahl, Adrian Kosowski, Jan Chorowski +6 authors
A 150M-parameter reasoning model using recurrent latent reasoning and in-context learning achieves a new cost-accuracy frontier on ARC-AGI-1.
50 篇论文 · 按点赞排序
Mind Lab, Vin Bo, Asher Cai +73 authors
Macaron-V1 is an open agent-model family that uses a Mixture-of-LoRA architecture and recursive self-improvement to enable continual learning and collaboration across specialized tasks.
Zhuoyang Qian, Biao Wu, Yiran Wang +6 authors
Spark-to-Paper is a lightweight, composable workflow inside coding assistants that generates research papers by separating planning from reporting, enforcing evidence-based claim revision, and using integrity checks to reduce fabrication.
Yunhao Chen, Xin Wang, Yixu Wang +6 authors
OpenART introduces a scalable red-teaming arena with evolving stateful environments to evaluate long-horizon AI agent safety, using the EMHA attack policy to expose increasing failure rates as task complexity grows.
Yijiang Li, Bingyang Wang, Yijun Liang +3 authors
Unsupervised on-policy self-distillation improves large language models by using internal consistency and majority-vote pseudo-solutions to correct confident errors without external supervision.
Qianggang Ding, Xingyao Wang, Rui Feng +19 authors
Combodied Agents integrate digital and embodied tools into a closed-loop framework that models individual human-state trajectories over time to provide proportionate, consent-aware support.
Zihao Liu, Xiaolong Shen, Zhenglin Zhou +2 authors
Latent-to-4D enables reusable direct 4D generation from video diffusion latents via alignment with a pretrained decoder and spatiotemporal attention, transferring across generators without retraining.
Yuanyang Yin, Gongxuan Wang, Yifan Zhan +3 authors
Evoke is an interactive world model that uses external persistent memory and a redesigned long-horizon teacher to enable responsive, open-ended video generation with bounded context and low latency.
Qing Zong, Jiayu Liu, Junhao Shen +9 authors
Agentic systems can achieve open-ended improvement through multi-component co-evolution that progressively removes fixed human constraints across agents, environments, and evolution mechanisms.
Yuling Shi, Jinghan Xu, Kelin Fu +12 authors
SWE-Bench ProMax is a rigorously curated multilingual benchmark of large-scale code refactoring tasks that reveals substantial unsolved challenges for current AI coding agents.
Alexander Panfilov, David Schmotz, Ilia Shumailov +5 authors
Encrypted reasoning traces shared across sessions and models can be intercepted and injected into weaker models to extract proprietary reasoning, private data, hidden hazards, and hidden prompts.
Cheng Qian, Wenting Zhao, Liangwei Yang +6 authors
Stronger models can build inference-time harnesses that substantially improve weaker models' task performance without parameter updates by offloading reasoning into structured code and routing.
Yifan Zhang, Yutong Dai, Juntao Tan +9 authors
DarwinX evolves agent harnesses via population selection with frozen models, improving verified performance across benchmarks without benchmark-specific patches.
Tao Feng, Fangxu Yu, Haozhen Zhang +9 authors
LLM routing is formalized as a sequential decision process with a unified benchmark and modular infrastructure to compare and improve cost-effective model selection.
Zongchuang Zhao, Xin Zhou, Tianyang Xu +5 authors
SimWAM trains a lightweight action planner using video generation as a training signal, enabling efficient trajectory prediction without future generation at inference and supporting reinforcement learning optimization.
DreamX Team, Rui Chen, Xiangxiang Chu +7 authors
DreamX-Phi 1.0 is an action-conditioned video world model for robotic manipulation that uses geometric attention encoding, depth estimation, object masks with a frozen teacher, and distillation to generate faithful future observations.
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.
Mengru Wang, Junfeng Fang, Shuofei Qiao +16 authors
Mechanist is an autonomous agentic system that uses AI to discover and control the mechanisms underlying model intelligence, generating hypotheses, performing causal interventions, and improving safety and performance.
Xingyu Tan, Xiaoyang Wang, Qing Liu +4 authors
SkillZip compresses reusable procedural skills into contract-preserving, executable graph units to enable efficient retrieval and expansion under limited context budgets.
Lei Bai, Jiaqi Cao, Chiyu Chen +122 authors
Intern-S2-Preview is a scientific agentic foundation model series that integrates multimodal pre-training, multi-task reinforcement learning, and memory-augmented extensions to support long-horizon scientific reasoning and forecasting.
Yaxin Luo, Haobin Jiang, Jialv Zou +11 authors
AutoDesign uses a meta-harness optimizer to recursively improve a code agent for structured media generation, achieving state-of-the-art results on paper-to-poster synthesis.
Kejian Zhu, Zhuoran Jin, Shangqing Tu +5 authors
Reinforcement learning enables stable multi-task reasoning in large language models through sparse, near-orthogonal parameter updates, unlike supervised fine-tuning which suffers from task conflicts, motivating a decoupled Parallel-RL training approach.
Xiaomin Li, Yuexing Hao, Jianheng Hou +90 authors
MatrAIx is a large-scale simulated-user evaluation framework that uses diverse persona records and interactive environments to test AI systems across many domains.
Daeun Lee, Jaeah Lee, Woosung Kim +2 authors
A rest-state framework reconstructs articulated objects from a single closed configuration by fusing vision-language outputs into consistent part meshes and validating synthesized motion hypotheses via geometric consistency.
Taeil Kim, Kangsan Kim, Sung Ju Hwang
Agent Memory Distillation improves small language model tool-use performance by transferring structured hierarchical memory from a large teacher agent without additional training.
Ming Li, Chenguang Wang, Xirui Li +5 authors
Rhetorical framing significantly biases AI scientific review scores in structured ways, with effects shaped by reviewer identity, score range, and evaluation strictness rather than rewriting complexity.
Junghwan Lim, Joon Son Chung, Sungmin Lee +24 authors
Motif 3 is a large sparse mixture-of-experts language model using grouped differential latent attention and specialized training techniques to achieve strong reasoning, coding, and long-context performance.
Kaixin Ding, Xi Chen, Minghong Cai +9 authors
PlayWorld benchmarks interactive video world models by using multi-modal agents to pursue long-horizon objectives, evaluating geometry consistency, interaction fidelity, and state evolution.
Kejian Zhu, Zhuoran Jin, Dongqi Huang +4 authors
Effective multimodal agent training is improved by selecting diverse environments via ability-aware selection and structuring difficulty through hierarchical curriculum learning.
Haokai Zhang, Yuhang Ding, Yunshu Zhou +5 authors
A frozen vision-language model improves spatial reasoning by self-evolving through verified experience, reflection, and reusable memory retrieval without parameter updates or external tools.
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