arXiv:2607. 12640v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producing a stronger agent.
arXiv:2606. 05597v3 Announce Type: replace Abstract: Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle GPUs in synchronous RL, and trajectories that use more steps and tokens than necessary.
arXiv:2609. 22041v1 Announce Type: new Abstract: Reinforcement learning is increasingly used to align image generators with reward signals, and Flow-GRPO recently extended this paradigm to flow-matching models by treating the denoising sampler as a stochastic policy that can be optimized from reward feedback.
arXiv:2606. 07845v1 Announce Type: cross Abstract: We measure how well current large language models coordinate as multiple agents sharing a common resource, using the dining philosophers problem as a clean test bed.
arXiv:2607. 09042v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, but every update consumes robot rollouts that are slow and costly to collect, making sample efficiency a central concern.
arXiv:2608. 04788v1 Announce Type: cross Abstract: Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens should be updated.
arXiv:2608.29296v1 Announce Type: cross Abstract: Larger batches reduce the variance of stochastic gradients per update and are therefore often expected to accelerate training. Yet whether this stati...
arXiv:2607. 25091v1 Announce Type: new Abstract: The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms have not been systematically investigated.
The paper investigates why Group Relative Policy Optimization (GRPO) benefits from per‑prompt normalization by examining the local curvature of the sequence‑level policy gradient. It shows that standard deviation normalization acts as an adaptive gradient, yielding a provably faster convergence rate than unnormalized REINFORCE under mild conditions, with the improvement tied to the average within‑prompt reward standard deviation. The authors also propose IS‑GRPO, an importance‑sampling variant that maintains alignment with the full gradient and offers a tighter convergence guarantee, and empirically validate these theoretical insights on GSM8K and MATH datasets at 1.5B and 7B model scales.
The paper introduces LRE (Learned Relevance Eviction), a lightweight, CPU‑only, language‑model‑free scorer that learns which parts of an agent’s interaction history are task‑critical and preserves them verbatim. In experiments, LRE matches or surpasses baseline eviction policies on accuracy‑cost trade‑offs, recovers 93% of full‑history accuracy, reduces worst‑case prompt size by 52%, and outperforms dense and token‑pruning encoders in conversational memory while being 295–1569× smaller. The method also achieves superior budgeted answer quality on LoCoMo reading and can be trained annotation‑free, recovering 95% of supervised scorer performance.
The paper introduces WebMRE, an offline benchmark comprising 541 tasks and 5,293 steps extracted from WebArena trajectories, designed to provide deterministic scoring for web agents without live environments. It enables the first systematic study of how guide sentences and grounded actions reinforce each other, showing that jointly decoding a guide improves element selection accuracy and that the guide acts as a causal instruction channel. The authors fine‑tune models that outperform leading zero‑shot baselines on all offline metrics.
Reinforcement learning from verifiable rewards (RLVR) for mathematical reasoning suffers from a structural blind spot: on "cliff" prompts-those on which every sampled rollout in a group fails-the group-normalized advantage is identically zero, so GRPO produces no gradient on precisely the prompts at the frontier of the model's capability. We introduce LoRA Scaffolded Policy Optimization (LSPO), a sampling-time mechanism that recovers this lost gradient.
arXiv:2609.36642v1 Announce Type: new Abstract: Language-model agents are usually trained by reinforcement learning from one reward per episode, and privileged self-distillation enriches it by lettin...