每天自动聚合 AI 领域最新动态
Expert human readers process large inputs (e.g., code repositories and long documents) by skimming to closely read on...
Next Best Action (NBA) systems must select among customer interventions (e.g., discounts, promotions, and lifecycle a...
Despite advancements in automatic speech recognition systems (ASR), current systems exhibit speaker-attribute bias, i...
Beyond basic tool use and coding skills, effectively incorporating visual references into agentic generation is equal...
Agent learning is shifting from learning from human data toward learning through interaction with the world. However,...
Frontier agents retrieve structural metadata well and compute geometry from coordinates less reliably. We ask how muc...
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for assoc...
LLM agents that compute the right answer can still answer wrongly. Agent harnesses increasingly keep long tool output...
Systems that combine several large language models (LLMs) often use one context for many questions. When the context ...
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agen...
A seemingly reasonable push in Sokoban can make the puzzle unsolvable. To avoid such mistakes, an agent has to antici...
Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters t...