Adversarial-Training

TL;DR for operators A preference-tuned model can look stable under ordinary evaluation and become less reliable once production decoding introduces more randomness. That gap is the main reason to pay attention to GANPO. The paper’s standard alignment gains are real but not large. On length-controlled AlpacaEval, adding GANPO raises DPO from 27.79 to 29.69 for Gemma2-2B-it and from 32.34 to 33.87 for Llama3-8B-Instruct. The SimPO gains are similarly modest: 36.03 to 36.74 and 48.31 to 50.48. Response length stays essentially unchanged. ...

Kitchen work is not hard because chopping onions is metaphysically difficult. It is hard because two people must agree, implicitly and quickly, who gets the onion, who holds the plate, who waits by the pot, and who moves out of the corridor before everyone performs a small culinary traffic accident. That is why Overcooked remains such a useful multi-agent benchmark. It turns coordination into something visible. Agents do not merely need to “perform a task”; they need to infer what another agent is about to do and avoid becoming a sentient obstacle. ...