Search papers, labs, and topics across Lattice.
6
0
8
5
A proactive memory agent can significantly enhance decision-making in long-horizon tasks by preventing critical information from being forgotten.
Stronger coding agents can achieve higher success rates while requiring fewer user interventions, reshaping our understanding of effective coding assistance.
Selective teacher intervention in multi-turn training can boost agent performance by over 13% by mitigating the impact of early errors.
Chunk-level semantic verification in OmniOPD yields a +28.64% boost in math performance over traditional OPD, challenging the reliance on token-level logit matching.
On-policy RL for machine learning engineering agents is now practical, thanks to a synthetic sandbox that slashes execution time by 13x while boosting performance by up to 67%.
Achieve significant reasoning gains in frozen LLMs (+22.4%) without retraining by adaptively routing reward model guidance at the token level during inference.
