7,908 papers across 0 tags. Search by title or author; sort by new & hot, trending, citations, and more. Click any card to open the paper.
Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world
Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs
Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the mo
Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most exist
Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis m
Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interaction feedback and s
Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. A
Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities a
General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent d
Role-playing language agents (RPLAs) should play characters whose values and behavior evolve as the story progresses, not maintain a fixed persona. Existing benchmarks m
Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced fronti
Planning for real-world problems by language models often involves both world and user constraints, which may not be fully specified upfront and are progressively disclose
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, b
Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, but Korean agentic b
Large Language Models (LLMs) are undergoing a fundamental transformation from conversational generators into integrated AI systems capable of reasoning, action, memory, an
Multi-agent reasoning systems adopt a "generate-then-transfer" paradigm that forces end-to-end latency to scale linearly with pipeline depth. We introduce StreamMA, a mu
The recent success of agent swarms has shifted the paradigm of large language model (LLM)-based agents from single-agent workflows to multi-agent systems, highlighting the
Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot
Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, expe
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and act
Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows re
World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models
Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-docume