Tag archive
A team calling itself NeoHorse released NeoHorse-1, a system that records which model handled each user request and how it went, then converts those logs into training data for the next round, closing an evaluation-to-training loop the authors presen
If you followed our earlier posts, you saw big claims: nine agents, one gym, zero human intervention....
I Tried Post-Training and All I Got Was "systemsystem" I followed the TRL tutorial to...
EnvHarness, FACET, and SPADE all took the top spots on Hugging Face's daily paper list with the same underlying move, shifting effort from making the agent smarter to manufacturing the environments the agent practices in, with FACET releasing 6,020 r
A token-level analysis found that reinforcement learning's entire benefit to reasoning models is concentrated at a tiny number of uncertain decision points, and a training-free method reproduced most of it for roughly a thousandth of the cost.
U-OPSD drops the teacher entirely: it samples several attempts, takes a majority vote as a stand-in answer, then trains only on the attempts that disagreed with that vote, matching or beating methods that use real ground-truth labels.
Forsy-AI/agent-apprenticeship treats completed agent work as portable 'experience compilations' you can install into later runs. Broad agent
A new paper shows a frozen small language model's accuracy on a hard math test can jump from 80.0% to 93.3% simply by grafting a byte-exact cache of verified solutions into it, with no weight changes at all.