Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Adaptively Coordinating with Novel Partners via Learned Latent Strategies
Authors: Benjamin Li, Shuyang Shi, Lucia Romero, Huao Li, Yaqi Xie, Woojun Kim, Stefanos Nikolaidis, Charles Lewis, Katia Sycara, Simon Stepputtis
NeurIPS 2025 | Venue PDF | LLM Run Details | Input Tokens: 22,163 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,016 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our method in a modified version of the Overcooked domain... Through these experiments and an online user study, we demonstrate that our proposed agent achieves state of the art performance compared to existing baselines when paired with novel human, and agent teammates. |
| Researcher Affiliation | Academia | 1Carnegie Mellon University 2University of Pittsburgh 3University of Southern California 4Virginia Tech |
| Pseudocode | Yes | Algorithm 1 Strategy-Conditioned Cooperator Training Algorithm 2 Online Adaptation to Novel Partners with Fixed-Share |
| Open Source Code | Yes | We provide the code for our proposed agent, as well as instructions of how to re-train our TALENTS agent |
| Open Datasets | No | This work does not provide a dataset. The dataset used to train our VAE can be re-generated using our provided code. |
| Dataset Splits | Yes | Train/Validation Split 80/20 Data split ratio (%) |
| Hardware Specification | Yes | All models were trained on a server with 2 AMD EPYC 7713 64-core processors, 1.08 TB of system memory, and 5 Nvidia RTX 6000 Ada GPUs. |
| Software Dependencies | No | The paper text does not explicitly provide specific software versions (e.g., Python, PyTorch versions) for replication. |
| Experiment Setup | Yes | Encoder training hyperparameters are listed in table A.2, and were tuned via a simple linesearch. Cooperator Training hyperparameters can be found in table A.3. |