This work asks whether replacing free-form reasoning with a restricted, executable program turns this sparse reward into a graded, more interpretable training signal, using a standard SFT → RLOO pipeline as the reference point.
This work shows that training a strong instruction-tuned reasoning model on its own answer-conditioned chains sharply lowers its verifiable-reasoning accuracy, and generates answer-blind data, because no correctness filter can see this damage in the data.
Jungseob Lee, Seungyoon Lee, Suhyune Son et al.· arXiv.org· 0 citations
A neuro-symbolic Program-of-Thought pipeline in which a 4B backbone writes a program rather than stating an answer directly, which yields correct, verifiable deductions at the 4B scale, and the residual difficulty lies in premise selection rather than the deduction itself.
Quoc-Khang Tran, M. Nguyen, P. Thai et al.· arXiv.org· 0 citations
This work systematize the RL-for-LLM paradigm and provides a compute-centric analysis of prominent post-training algorithmic frameworks: Proximal Policy Optimization (PPO), Group Relative Policy Optimization (GRPO), as well as their variants, and develops a taxonomy of intra- and inter-model parallelism strategies for...
Maciej Besta, L. Schmidt, Lara Nonino et al.· 0 citations
Reason Popper-ly, a neurosymbolic framework that uses inductive logic programming (ILP) to learn relation composition rules from reasoning traces and deploys them as an online verifier for step-level correction, consistently improves terminal accuracy over standard CoT.
A unified supervision framework is introduced that embeds programmatically verifiable checkers into synthesized instruction-conflict instances, enabling alignment without oracle labels or reasoning traces, supporting both instruction-tuned and reasoning models.
Sian-Yao Huang, Li-Hsien Chang, Che-Yu Lin et al.· Neural Information Processin...· 4 citations
This work makes execution time learnable through three stages: how code is tested, by building DMC-Optim with large optimization tests and a calibrated sandbox; how speed is turned into reward, by composing correctness and speed in the RL environment and using an offline simulator to predict the most promising configur...
Pierre Chambon, Kun-Hao Zheng, Juliette Decugis et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
