Agents
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering John Y ang Carlos E. Jimenez
SWE-bench test instances (SWE-bench Lite) to analyze our ACI design choices.
Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
In this paper, we propose a Hybrid Multimodal Memory module to address the above challenges.
RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
However, the existing method heavily relies on human-annotated agent profiles (e.g., name, age, personality, relationships with others,
Jiashi Gao
In this context, our work rigorously addresses the critical concern: Does egalitarian fairness lead to instability?
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination Xihuai Wang
The significant difference between the deployment-time partners' distribution and the training partners' distribution determined by the
Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
Figure 1: Complex decision problems that require a good understanding of the environment's
Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Among the research topics in multi-agent learning, mixed-motive cooperation is one of the most prominent challenges, primarily due to the mismatch between individual and collective goals.
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
Left: A human partner is confined to a wheelchair and struggles to move past an obstacle.
