Tag
This paper proposes a modular framework using Activated LoRA adapters and a context-aware routing mechanism to efficiently mitigate harms in large language models, improving safety alignment while preserving task performance.
ModularRSI introduces a modular and generalizable framework for recursive self-improvement in AI agent harnesses, using contrastive learning across tasks to evolve modules independently and enhance performance on unseen tasks.
This paper introduces Modular TTT, a framework that represents test-time training inner learners as directed acyclic graphs, enabling systematic ablation and composition of components. The authors train 410M and 1.45B parameter models on 100B tokens, achieving performance comparable to GatedDeltaNet.
Presents MKEvolve, a modular multi-agent framework that iteratively co-evolves modular decomposition and LLM-generated kernels for hardware accelerators, achieving improved correctness and speedup over direct synthesis while reducing token usage.
CaVe-VLM-CoT is a modular reflection-based agentic-RAG framework for vision-language models that enforces evidence-grounded reasoning through a five-stage pipeline, achieving 87.1% accuracy on ScienceQA and proposing a suite of 23 metrics for evaluation.
Introduces AgentSpec, a modular specification framework for systematically composing and analyzing embodied LLM agent scaffolds, revealing that performance depends on scaffold compatibility and interaction effects rather than isolated module strength.
Palette proposes a modular framework for selectively relaxing safety refusal behaviors in LLMs for authorized professional domains, using multi-objective search and lightweight adaptation to avoid costly retraining.
GeoStack introduces a geometric framework to compose independently trained domain experts in Vision-Language Models without catastrophic forgetting, achieving constant-time inference and a 10x reduction in geometric error.