Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,023 papers.
25 Aug 2026
Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated programs, or a single domain. We introduce FrontierChallenge, a cross-domain benchmark comprising 300 end-to-end scientific workflows.
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.
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.
Chao Song, Yiyan Qi, Xixi Wu et al. · 23 Mar 2026
Reinforcement learning for large language models requires careful consideration of reward shaping, model scaling, data composition, algorithm selection, and environmental stability to achieve optimal performance in complex multi-turn planning tasks.
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…
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…
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…
Caiming Xiong, Xiao Wang, Jiaqi Liu et al. · 19 May 2026
Automating scientific discovery requires more than generating papers from ideas.
Jakob Foerster, Jeff Clune, Jenny Zhang et al. · 19 Mar 2026
Hyperagents represent a self-referential framework that integrates task and meta-agents into a single editable program, enabling metacognitive self-modification and open-ended improvement across diverse computational domains.
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,…
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.
1 May 2026
AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets.
28 May 2026
Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The long-horizon goal of an AI that can figure out how to improve itself remains open.
31 Aug 2026
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…
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.
2 Sep 2026
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and verification, but this architecture still leaves domain-specific know-how outside the agent.
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…
26 Aug 2026
Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying foundation model.
12 Aug 2026
Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context.
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.
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…
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.
13 Aug 2026
Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consolidation, invoking LLMs after each interaction to extract, summarize, or update memories.