Open library
The essential reading of generative AI and agents, open in a clean reading view, with Meow and Standard summaries when available. No account needed to read.
563 papers · 561 with a Meow summary · 333 posts
The selected papers and blogs: the essential papers of generative AI and agents, and the key lab publications and essays, each with Meow and Standard summaries.
MiroMind Team
We present MiroThinker-1.7, a new research agent designed for complex long-horizon reasoning tasks. Building on this foundation, we further introduce MiroThinker-H1, which extends the agent with heavy-duty reasoning capabilities for more reliable multi-step problem solving. In particular, MiroThinker-1.7 improves the…
Yuan Liang, Ruobin Zhong, Haoming Xu et al.
Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently “reinvent the wheel”, rediscovering solutions in isolated contexts wit…
REDSearcher Team
Large language models are transitioning from general-purpose knowledge engines to real-world problem solvers, yet optimizing them for deep search tasks remains challenging. The central bottleneck lies in the extreme sparsity of high-quality search trajectories and reward signals, arising from the difficulty of scalabl…
InternScience Team, Shanghai Artificial Intelligence Laboratory
Artificial intelligence is rapidly emerging as a powerful engine for scientific discovery. Modern machine learning and large language models support literature analysis, hypothesis generation, experimental planning, and data interpretation across biology, chemistry, and earth science. These advances have inspired AI S…
Jun Han, Shuo Zhang, Wei Li et al.
Financial markets are noisy and non-stationary, making alpha mining highly sensitive to backtest noise and regime shifts. While recent agentic frameworks improve automation, they often lack controllable multi-round search and reliable reuse of validated experience. To address these challenges, we propose **QuantaAlpha…
Jianhao Ruan, Zhihao Xu, Yiran Peng et al.
Language agents have shown strong promise for task automation. Realizing this promise for increasingly complex, long-horizon tasks has driven the rise of a sub-agent-as-tools paradigm for multi-turn task solving. However, existing designs still lack a dynamic abstraction view of sub-agents, thereby hurting adaptabilit…
Jiefeng Chen, Bhavana Dalvi Mishra, Jaehyun Nam et al.
A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and opaque performance attribution. Current LLM-based agents struggle here, often genera…
Multimodal large language models (MLLMs) have achieved remarkable success across a broad range of vision tasks. However, constrained by the capacity of their internal world knowledge, prior work has proposed augmenting MLLMs by “reasoning-then-tool-call” for visual and textual search engines to obtain substantial gain…
Taofeng Xue, Chong Peng, Mianqiu Huang et al.
The development of native computer-use agents (CUA) represents a significant leap in multimodal AI. However, their potential is currently bottlenecked by the constraints of static data scaling. Existing paradigms relying primarily on passive imitation of static datasets struggle to capture the intricate causal dynamic…
Tianxin Wei, Ting-Wei Li, Zhining Liu et al.
**Abstract:** Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, exemplified by standard benchmarks in mathematics and code, they struggle in open-ended and dynam…
Wei Zhou, Xuanhe Zhou, Shaokun Han et al.
Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information storage, retrieval, update, consolidation, and dynamic lifecycle governance throughout agent execution. Despite this evolution, existing evaluat…
Jingdi Lei, Di Zhang, Junxian Li et al.
Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and often fails to ensure effective context utilization. We propose $\delta$-mem, a lightweight memory mechanism that augments a frozen full-at…
Hanxiang Chao, Yihan Bai, Rui Sheng et al.
Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new evidence emerges. We identify a critical and underexplored failure mode, **Implicit…
Chenyu Zhou, Huacan Chai, Wenteng Chen et al.
Large language model (LLM) agents are increasingly built less by changing model weights than by reorganizing the runtime around them. Capabilities that earlier systems expected the model to recover internally are now externalized into memory stores, reusable skills, interaction protocols, and the surrounding harness t…
Zefeng He, Siyuan Huang, Xiaoye Qu et al.
Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downstream tasks. Inspired by the success of advanced agent frameworks such as Claude Code, we propose **GEMS** (Agent-Native Multimodal **GE**ne…
Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present **LoGeR** (**Lo**ng-context **Ge**ometric **R**econstruction), a novel architecture…
Haozhen Zhang, Quanyu Long, Jianzhu Bao et al.
Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-code human priors about what to store and how to revise memory, making them rigid under diverse interaction patterns and inefficient on long histories. To this…
Hong Liu, Jiaqi Zhang, Chao Wang et al.
While Mixture-of-Experts (MoE) architectures have become the standard for sparsity scaling in large language models, they increasingly face diminishing returns and system-level bottlenecks. In this work, we explore embedding scaling as a potent, orthogonal dimension for scaling sparsity. Through a comprehensive analys…
LLM agents have demonstrated remarkable capabilities in software development, but their performance is hampered by long interaction contexts, which incur high API costs and latency. While various context compression approaches such as LongLLMLingua have emerged to tackle this challenge, they typically rely on fixed me…
Jiaqi Liu, Yaofeng Su, Peng Xia et al.
To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to substantial redundancy, or rely on iterative reasoning to filter noise, incurring high t…
Zongxia Li, Zhongzhi Li, Yucheng Shi et al.
AI agents have become increasingly capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on relatively simple problems that finish within a few minutes and are typically evaluated only by their final outcome. This setup overlooks intermediate progress and p…
Shaoqiu Zhang, Yuhang Wang, Jialiang Liang et al.
Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieva…
Shuangrui Ding, Xuanlang Dai, Long Xing et al.
Large language and vision-language models increasingly power agents that act on a user’s behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete rea…
Zhuofeng Li Haoxiang Zhang Cong Wei Pan Lu Ping Nie, Yi Lu Yuyang Bai Shangbin Feng Hangxiao Zhu Ming Zhong Yuyu Zhang, Jianwen Xie Yejin Choi James Zou Jiawei Han Wenhu Chen Jimmy Lin et al.
Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-$k$ retrieval step before reasoning. This abstraction is efficient, but for agentic search, it becomes a bottleneck: exact lexical constraints, sparse clue conjunctions,…
Yuxuan Zhang , Yubo Wang , Yipeng Zhu , Penghui Du , Junwen Miao , Xuan Lu ,
AI agents may be able to assist with emails and documents, but can they reliably complete everyday online workflows on real websites? Everyday online tasks offer a realistic yet unsolved testbed for evaluating the next generation of AI agents. To this end, we introduce ClawBench, an evaluation framework comprising 153…
Bowen Ye, Rang Li, Qibin Yang et al.
Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and robustness evaluation, and narrow coverage of modalities and interaction paradigms. W…
Video-MME Team
With the rapid advancement of video understanding, existing benchmarks are becoming increasingly saturated, exposing a critical discrepancy between inflated leaderboard scores and real-world model capabilities. To address this widening gap, we introduce **Video-MME-v2**, a comprehensive benchmark designed to rigorousl…
Yujian Liu Jiabao Ji Li An Tommi Jaakkola Yang Zhang Shiyu Chang
Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts focus on overly idealized conditions, where LLMs are directly provided with hand-c…
Shiva Krishna Reddy Malay, Shravan Nayak, Jishnu Nair et al.
Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by benchmarks that fail to capture the intricacies of professional environments, specifically, the need for long-horizon plann…
Qiyuan Zhang, Junyi Zhou, Yufei Wang et al.
As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the community lacks a unified benchmark to assess this evaluation paradigm, as existing…
Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov et al.
Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of large-scale task collections with reproducible execution environments and reliable test suites. Although a growing number of benchmarks have e…
Xiangyi Li, Yimin Liu, Wenbo Chen, Bingran You, Zonglin Di,
Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired wi…
Alisia Lupidi, Bhavul Gauri, Thomas Simon Foster et al.
LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks sourced from state-of-the-art machine learning papers. These tasks span diverse domains, including language modeling, mathematics, bioinfo…
Multimodal Large Language Models (MLLMs) have advanced VQA and now support Vision-DeepResearch systems that use search engines for complex visual-textual fact-finding. However, evaluating these visual and textual search abilities is still difficult, and existing benchmarks have two major limitations. First, **existing…
Yinger Zhang, Shutong Jiang, Renhao Li et al.
While agent evaluation has shifted toward long-horizon tasks, most benchmarks still emphasize local, step-level reasoning rather than the global constrained optimization (e.g., time and financial budgets) that demands genuine planning ability. Meanwhile, existing LLM planning benchmarks underrepresent the active infor…
Yibo Wang, Lei Wang, Yue Deng et al.
Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benchmarks often require annotation-intensive task construction, rely on static evaluation dimensions, or fail to reliably verify facts when citations are missing.…
Zhongzhi Li, Yucheng Shi, Zongxia Li et al.
High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instruction, environment, reference solution, and verifier mutually consistent. Human authoring does not scale, and direct generation with large…
Jiacheng Liu, Xiaohan Zhao, Xinyi Shang et al.
Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code and further comparing it with two independent open-source AI agent systems, Ope…
Ruixiang Zhang Richard He Bai Huangjie Zheng Navdeep Jaitly Ronan Collobert
Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement learning? We answer in the affirmative with simple self-distillation (SSD): sample solutions from the model with certain temperature and truncation configurations, then fine…
Zhongxing Xu, Zhonghua Wang, Zhe Qian et al.
Recent advancements in multimodal large reasoning models (MLRMs) have significantly improved performance in visual question answering. However, we observe that transition words (e.g., because, however, and wait) are closely associated with hallucinations and tend to exhibit high-entropy states. We argue that adequate…