AI Agent & Automation Workflows

Train RL on diverse agent frameworks (LangChain, AutoGen, custom) via unified data interface and transition-based RL decomposition.

Train LLM-based agents with end-to-end RL by extending MDPs to handle tool invocation and environmental stochasticity—enable dense process rewards for intermediate steps and masked policy gradients for learnable actions.

Guide frozen language models toward multi-step reasoning by modifying cached key-value representations after the prefilling stage. Extract steering vectors from contrastive prompt pairs and apply them to KV cache with scalar coefficients. Improves reasoning on GSM8K, ARC, CommonsenseQA while adding only 10ms overhead per token.

Enable small vision-language models to reason over diverse data types by converting latent embeddings into visual representations, achieving specialized performance without domain-specific training.

Brain-inspired framework integrating spatial, temporal, episodic, and semantic memory systems for embodied agents. Achieves 26.5% performance improvement via dynamic spatial knowledge graphs and closed-loop planning with critic modules.

Route queries across frontier models using two-stage system: graph-based task discovery identifies ~332 latent task types via semantic similarity + preference patterns; MoE with task-specific adapters estimates quality for candidate models. Achieves <50% inference cost of strongest single model while exceeding its performance; applies when managing pools of frontier models with narrow capability gaps.

Create real-time full-body talking avatars for AR using hybrid parametric-Gaussian representations. Teacher-student distillation transfers pose-dependent deformations from a large network to a compact student model, enabling 90+ FPS rendering on mobile devices.

Apply test-time register token injection to pre-trained Vision Transformers without retraining, eliminating high-norm outlier artifacts and improving attention map quality.