arXiv:2606. 27369v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the ground-truth solution is unknown.
arXiv:2607. 02141v1 Announce Type: new Abstract: Most LP-from-text benchmarks are static datasets of word problems written and labeled by hand.
arXiv:2606. 18284v1 Announce Type: cross Abstract: The limiting resource for training agents via reinforcement learning (RL) is increasingly frontier task supply: valid, solvable tasks just difficult enough to train the current model.
arXiv:2607. 25970v1 Announce Type: cross Abstract: RL for code correctness is now established: have the model generate a program, run it against hidden test cases, and reward solutions that pass.
arXiv:2606. 15197v1 Announce Type: cross Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments.
Mixed-Integer Linear Programming (MILP) is a fundamental problem class in operations research and combinatorial optimization, with broad applications to industrial decision-making. Owing to their NP-hardness, however, modern solvers may struggle to find high-quality solutions for challenging MILP instances within practical time limits.
Online Self-Weighted Fine‑Tuning (OSW‑FT) augments standard supervised fine‑tuning by adding online, trajectory‑level weighting: for each query the model estimates its current success rate from a small number of inference‑only rollouts and rescales the SFT loss accordingly. The method keeps the optimization direction anchored to the expert trajectory while adapting the update magnitude online, and it is shown to be unbiased for any finite rollout count with a convergence analysis. Across Qwen3 models from 0.6B to 4B, OSW‑FT consistently outperforms plain SFT on challenging benchmarks such as AIME, achieving a favorable compute‑performance trade‑off with only two online rollouts.
arXiv:2604. 20209v2 Announce Type: replace Abstract: LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both improve together.
arXiv:2606. 09052v1 Announce Type: cross Abstract: Self-evolution offers a scalable path to stronger reasoning: a pretrained language model improves itself with only minimal external supervision.
arXiv:2607. 25675v1 Announce Type: new Abstract: Text-space optimization adapts large language models (LLMs) by editing external natural-language artifacts rather than model weights, so the optimized artifacts remain inspectable and the model can be treated as a black box.
arXiv:2606. 05464v1 Announce Type: new Abstract: Verifiable reward training has improved mathematical and coding reasoning, but these domains capture only part of step-by-step decision making.
arXiv:2608. 01522v1 Announce Type: new Abstract: Teaching a language model a skill it has not mastered is obstructed by three recurring difficulties: training data is scarce, ground-truth reasoning traces are usually unavailable, and models often exhibit an apparent ceiling beyond which additional data yields no further improvement.