Search papers, labs, and topics across Lattice.
7
0
9
28
This work identifies and formalizes this failure mode, which is term destructive resource preemption: obtaining the resources required for a requested task by terminating, overwriting, evicting, or degrading an incumbent task.
Rather than treating agent trajectories as dead post-training demonstrations, researchers can now resurrect thousands of fully executable, verifiable terminal environments directly from tool-execution logs.
Credit-addressable reasoning boosts multimodal geometry accuracy by over 8 points, revealing the critical role of structured learning in complex tasks.
Recursive belief updates in AgentOPSD reveal pivotal decision points, leading to a 89.1% success rate on complex RL tasks.
Even the best MLLMs struggle to meet user requirements, achieving only 66% coverage of essential task functions.
No current MLLM can reliably issue timely safety warnings, with performance sharply varying across domains and a troubling trade-off between recall and false positives.
Scaling up LLMs boosts combinatorial creativity in code generation, but plateaus on exploratory tasks, revealing a "convergence-by-scaling" effect where larger models become less divergent.
