SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
Paper
• 2502.04780 • Published
AI
-
-
Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations
Paper • 2502.11269 • Published • 1 -
From Autonomous Agents to Integrated Systems, A New Paradigm: Orchestrated Distributed Intelligence
Paper • 2503.13754 • Published • 1 -
Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
Paper • 2502.14321 • Published -
Generative Multi-Agent Collaboration in Embodied AI: A Systematic Review
Paper • 2502.11518 • Published -
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
Paper • 2504.01990 • Published • 303 -
NoLiMa: Long-Context Evaluation Beyond Literal Matching
Paper • 2502.05167 • Published • 16 -
Knowing When to Stop: Dynamic Context Cutoff for Large Language Models
Paper • 2502.01025 • Published -
LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion
Paper • 2501.15089 • Published • 1