3 accepted papers
Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. Existing agent frameworks usually rely on manually defined context engineering pipelines, such as multi-agent or post-hoc summary. We introduce Context Folding, a framework that empowers agents t…
Scaling test-time computation during language model inference, such as generating intermediate thoughts or sampling multiple candidate answers, has proven effective in improving model performance. While these techniques inherently rely on the stochastic nature of inference to explore diverse reasoni…
The training process of federated learning is known to be vulnerable to adversarial attacks (e.g., backdoor attack). Previous works showed that differential privacy (DP) can be used to defend against backdoor attacks, yet at the cost of vastly losing model utility. To address this issue, we in this…