Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.00494 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914175604752384 |
|---|---|
| author | Coda-Forno, Julian Zhao, Zhuokai Zhang, Qiang Tamboli, Dipesh Li, Weiwei Fan, Xiangjun Zhang, Lizhu Schulz, Eric Tseng, Hsiao-Ping |
| author_facet | Coda-Forno, Julian Zhao, Zhuokai Zhang, Qiang Tamboli, Dipesh Li, Weiwei Fan, Xiangjun Zhang, Lizhu Schulz, Eric Tseng, Hsiao-Ping |
| contents | Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base exchanges latent messages with a Coprocessor, and test two hypotheses aimed at improving latent communication over Liu et al. (2024): (H1) increase channel capacity; (H2) learn communication via joint finetuning. Under matched latent-token budgets on GPT-2 and Qwen-3, H2 is consistently strongest while H1 yields modest gains. A unified soft-embedding baseline, a single model with the same forward pass and shared representations, using the same latent-token budget, nearly matches H2 and surpasses H1, suggesting current dual designs mostly add compute rather than qualitatively improving reasoning. Across GSM8K, ProsQA, and a Countdown stress test with increasing branching factor, scaling the latent-token budget beyond small values fails to improve robustness. Latent analyses show overlapping subspaces with limited specialization, consistent with weak reasoning gains. We conclude dual-model latent reasoning remains promising in principle, but likely requires objectives and training schedules that explicitly shape latent spaces for algorithmic planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00494 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring System 1 and 2 communication for latent reasoning in LLMs Coda-Forno, Julian Zhao, Zhuokai Zhang, Qiang Tamboli, Dipesh Li, Weiwei Fan, Xiangjun Zhang, Lizhu Schulz, Eric Tseng, Hsiao-Ping Machine Learning Artificial Intelligence Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base exchanges latent messages with a Coprocessor, and test two hypotheses aimed at improving latent communication over Liu et al. (2024): (H1) increase channel capacity; (H2) learn communication via joint finetuning. Under matched latent-token budgets on GPT-2 and Qwen-3, H2 is consistently strongest while H1 yields modest gains. A unified soft-embedding baseline, a single model with the same forward pass and shared representations, using the same latent-token budget, nearly matches H2 and surpasses H1, suggesting current dual designs mostly add compute rather than qualitatively improving reasoning. Across GSM8K, ProsQA, and a Countdown stress test with increasing branching factor, scaling the latent-token budget beyond small values fails to improve robustness. Latent analyses show overlapping subspaces with limited specialization, consistent with weak reasoning gains. We conclude dual-model latent reasoning remains promising in principle, but likely requires objectives and training schedules that explicitly shape latent spaces for algorithmic planning. |
| title | Exploring System 1 and 2 communication for latent reasoning in LLMs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.00494 |