Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
24 Aug 2026
LLM agents remain unreliable on long-horizon tasks, where small local failures can compound over extended interactions and lead to overall task failure. Although external harnesses can substantially improve robustness, harness design remains a manual and expensive process that…
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.
Weijia Li, Fang Guo, Yanghua Xiao et al. · 18 Apr 2026
Long-horizon large language model (LLM) agents are fundamentally limited by context.
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.
9 Jul 2026
AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome.
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…
25 Aug 2026
Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Working Memory architecture for long-horizon agent harnesses, in which Working Memory…
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…
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.
21 Aug 2026
LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms including Prompt Engineering to elicit model capabilities, Context Engineering to manage information access, Harness Engineering to…
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…
Wenhu Chen, Yubo Wang, Yuxuan Zhang et al. · 9 Apr 2026
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.
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…
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…
13 Aug 2026
Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons.
20 Aug 2026
LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves.
29 Jul 2026
Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reasoning models.
23 Aug 2026
Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated: the proper unit is a declared model-plus-runtime configuration whose failures can occur in evidence acquisition, runtime routing,…
21 Aug 2026
Prompt injection is listed as the \#1 threat to AI agents. When an agent accesses external data from websites, files, or emails, an attacker may inject a prompt into the data, saying, "Ignore all prior instructions and perform <an attacker's task>." To prevent arbitrary…
24 Aug 2026
We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal without a central coordinator or scripted pipeline.