arXiv:2608. 02091v1 Announce Type: new Abstract: A bfloat16 transformer can train normally for many steps and then collapse abruptly.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2608.02091v2 Announce Type: replace Abstract: A bfloat16 transformer can train normally, then collapse abruptly. Prior work links collapse to structured attention errors and shows QK normalizat...
arXiv:2609.30820v1 Announce Type: cross Abstract: Looped transformers reuse weights across recurrence steps, making low-bit quantization especially attractive. We identify two distinct failure modes...
arXiv:2608. 03222v1 Announce Type: cross Abstract: Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates.
arXiv:2608. 02464v1 Announce Type: cross Abstract: LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the standard remedy, judging every step with a second LLM, costs more than the agent itself.
Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates. Failed runs tend to be longer and exhibit redundant exploration or looping, suggesting that some failures may be detectable before completion.
arXiv:2608. 02689v1 Announce Type: cross Abstract: We convert 21 of 28 full-attention layers of Qwen3-0.