Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
13 Aug 2026
Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation.
Caiming Xiong, Xiao Wang, Jiaqi Liu et al. · 19 May 2026
Automating scientific discovery requires more than generating papers from ideas.
27 Jul 2026
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is built on Kimi Delta Attention and Attention Residuals, which improve information flow across…
28 May 2026
Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks. However, existing evaluations often overlook the temporal dimension of tool use, especially the impact of tool response latency, and are usually limited to…
5 Jul 2026
Large language models have made research ideation increasingly accessible, yet effective idea development requires more than generating candidate directions. Researchers must ground a problem in current literature, identify meaningful bottlenecks, differentiate from existing…
19 Aug 2026
Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales.
Yang Liu, Ningyu Zhang, Huajun Chen et al. · 26 Feb 2026
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.
15 Aug 2026
Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate lessons from earlier executions, skip known procedures, or stop prematurely.
Yifan Yang, Ziyang Gong, Weiquan Huang et al. · 22 May 2026
Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback.
Weijia Li, Fang Guo, Yanghua Xiao et al. · 18 Apr 2026
Long-horizon large language model (LLM) agents are fundamentally limited by context.
14 Jul 2026
Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is controllable evolution, or adaptation, from experience with minimal or even no human input.
12 Jun 2026
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using…
Yong Wang, Xiangxiang Chu, Yiming Hu et al. · 9 Apr 2026
Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users,…
22 Jul 2026
As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring documents independently and aggregating via nDCG, ignoring…
7 Jul 2026
Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited generality, programmability, and rendering speed.
Cheng Qian, Yuanchen Bei, Xuying Ning et al. · 18 May 2026
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering.
4 Jun 2026
Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and exposes skill content as plaintext.
Seth Karten, Joel Zhang, Tersoo Upaa Jr et al. · 11 May 2026
Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents' long-horizon partial-observability decision-making.
Wei Wu, Ming Wu, Bingsheng He et al. · 16 May 2026
Memory is a fundamental component for long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, many stateful systems retain sequential autoregressive extraction or state-dependent…
18 Jun 2026
Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date: fourteen parallel implementation…
9 Jul 2026
In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context…
1 Aug 2026
AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior is mediated through a shared state that is repeatedly modified and reused across long-horizon…
8 Aug 2026
AI agents are becoming shared infrastructure, yet durable memory is commonly assembled from separate retrieval, governance, and operational components. We present SuperLocalMemory 4.0, a governed, local-first memory operating system for AI agents.
18 Aug 2026
Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon agentic reasoning introduces increasingly branching interactions and sparse rewards, exposing several limitations of RL: its heavyweight backpropagation-based training stack…