arXiv:2606. 25556v1 Announce Type: cross Abstract: Stepwise group-based RL is an attractive way to train long-horizon LLM agents without a learned critic: it reuses multiple sampled rollouts to estimate local advantages.
By Hanyang Wang, Weijieying Ren, Yuxiang Zhang, Ding Cao, Zhizhao Zeng, Ke Zeng, Tianxiang Zhao
arXiv:2608. 07719v1 Announce Type: new Abstract: Offline reinforcement learning repeatedly trains policies from a fixed transition pool, making redundant data costly across seeds and hyperparameters, while naive subsampling can remove rare transitions needed for long-horizon credit assignment.
By Ibne Farabi Shihab, Sanjeda Akter, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb, Anuj Sharma
arXiv:2607. 20129v1 Announce Type: new Abstract: Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocated without observing how a trajectory develops.
By El Hassane Ettifouri, Ayoub Belfatmi, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane
arXiv:2607. 11317v1 Announce Type: new Abstract: Low-bit quantization makes small reasoning models inexpensive to deploy but can degrade their chains of thought.
By El Hassane Ettifouri (Novelis Research, Paris, France), Ayoub Belfatmi (Novelis Research, Paris, France), Mahaman Sanoussi Yahaya Alassan (Novelis Research, Paris, France), Walid Dahhane (Novelis Research, Paris, France)
arXiv:2607. 28495v1 Announce Type: new Abstract: Stage-replay diagnostics reconstruct intermediate token prefixes and treat fresh-prefill continuation as continuation from the decoder state that originally reached the prefix.
By Alexander Boesgaard Lorup
arXiv:2606. 00257v1 Announce Type: cross Abstract: Token-level credit assignment for language-model reinforcement learning is usually formulated as if the policy were fully trainable, while practical LLM-RL pipelines often rely on parameter-efficient fine-tuning, especially LoRA.
By Rodney Lafuente-Mercado