This project explores various reinforcement learning techniques to improve model arithmetic reasoning beyond supervised imitation, and evaluates two RLOO extensions: dense rewards, which credits valid intermediate arithmetic steps, and an adaptive curriculum that uses a bandit policy to sample problem difficulty buckets based on recent learning signal.
This work introduces StructReward, a compute-efficient framework that provides dense reinforcement signals through structured step-level reward alignment and substantially reduces the computational overhead of multimodal reinforcement learning.
Desc descriptive evidence is provided that long-horizon multi-tool post-training can change ways of working that transfer beyond its training domain, and both software-engineering benchmarks improve despite the training collection containing no software-engineering tasks.
Sushant Mehta, Logan Ritchie, Liudas Panavas et al.· 0 citations
Reinforcement learning enables Agentic RAG systems to learn multi-turn search from verifiable outcome rewards, but all- zero rollout groups provide no comparative signal and may hide useful search behavior. We present EviBack, an evidence- constrained Teacher backoff that supplies auxiliary super- vision to such groups while preserving verifiable Actor re- wards. It separates evidence assessment from answer refine- ment, preventing reference answers from overriding evidence- insufficiency judgments. A fully automated, end-to-end GPT- 5.5-assisted APE pipeline starts from a manually authored single-prompt dual-task Teacher, automatically partitions and labels rollout data, and performs ablation, task decomposition, evaluation, and selection to produce a gated two-stage Teacher. Compared with the manual design, the resulting Teacher im- proves downstream F1 and valid-answer rate while reduc- ing search, duplicate queries, and forced termination. Across seven open-domain QA benchmarks and three Qwen3 scales, EviBack improves F1 over Search-R1 and raises both single- and multi-hop macro F1. We guarantee that the code will be made publicly available at a later stage.
This work reproduces SDPO's reported gains in its easy setting, then applies the identical setup to difficult tasks and finds that it does not teach anything, and explains this failure through a single causal chain from the loss to the model it produces.
Sarthak Harne, Chinmay Karkar, Yash Pandya et al.· 1 citation
Best Practice Critic Optimization (BPCO) is developed, a recipe that combines DPPO, value predictions bounded to the reward range, Monte Carlo value targets, unnormalized policy advantages, and length-adaptive generalized advantage estimation and shows that a carefully designed critic provides a reliable alternative to group-relative advantage estimation.
AdaKP is an online selector that re-chooses each problem's KP subset over the course of RL training, an entropy proxy that scores a KP by the reduction in next-token entropy it induces in a single inexpensive forward pass, with a provable bound on its truncation bias.
