Search papers, labs, and topics across Lattice.
The Chinese University of Hong Kong
7
0
12
7
Co-evolution in agentic systems could unlock unprecedented levels of adaptability, allowing agents to evolve beyond human-imposed limitations.
Agents struggle to maintain planning accuracy in complex tool ecosystems, with GPT-5.4's performance plummeting from 51.90% to 11.36% under severe blocking conditions.
Static reports are out; BioInsight's interactive system empowers researchers to dynamically explore and refine biomedical evidence like never before.
LLMs struggle with adaptive planning, achieving only 67.75% accuracy when faced with progressively revealed world and user constraints.
LMMs can't MacGyver their way out of a paper bag: they struggle to creatively repurpose objects in visually complex environments, revealing a critical gap in grounded reasoning beyond pattern recognition.
LRMs can often correct themselves even after making mistakes in their reasoning, hinting at a powerful, untapped "hidden critique ability" that can be unlocked with targeted interventions in the latent space.
Intrinsic reward signals in unsupervised RL for LLMs inevitably collapse due to sharpening of the model's prior, but external rewards grounded in computational asymmetries offer a path to sustained scaling.
