Model techniques map
Techniquespost-trainingreinforcement learning algorithm

specific method · filed under post-training

Negative-Advantage Penalties for Malformed Reasoning and Tool Calls

Assigning negative advantage to tokens responsible for malformed reasoning or tool calls.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we also penalize malformed reasoning and tool calls by assigning negative advantage to the offending tokens.

usedunclearin SWE teacher for Nemotron 3 UltraNVIDIA

Filed alongside

Other methods under post-training :: reinforcement learning algorithm.