arXiv:2607. 11953v1 Announce Type: new Abstract: Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut?
arXiv:2607. 11953v3 Announce Type: replace Abstract: Does a reinforcement-learning agent that earns high reward actually learn its task's hidden state, or only a shortcut that correlates with reward?
arXiv:2608. 05111v1 Announce Type: new Abstract: In partially observable reinforcement learning, agents face a dual bottleneck: they must explore to encounter rewarding states and retain that experience in memory to optimize their policies.
The paper proposes CANOPY, a minimalist reinforcement learning protocol that addresses two common pitfalls—signal starvation and policy drift—in outcome‑only RL for long‑horizon interactive tasks. By scaling same‑task exploration, keeping updates on‑policy, and anchoring updates with KL divergence, CANOPY enables a Qwen3‑14B agent to achieve top leaderboard results on the AppWorld coding benchmark without auxiliary supervision or elaborate scaffolding. The approach also improves performance on SWE‑bench for a Qwen3.5‑9B model.
The paper introduces On‑Policy Warmup (OPW), a teacher‑guided training stage where a student agent learns from a teacher on its own interaction trajectories before switching to reinforcement learning with verifiable rewards (RLVR). OPW differs from traditional imitation by focusing on states generated by the student’s own decisions, including imperfect actions and recovery situations. The authors provide a theoretical link between on‑policy reverse‑KL distillation and trajectory‑level distribution matching, showing that, under a competent teacher and low distillation loss, OPW can lower bound initial verifier success and reduce reward‑discovery complexity, thereby accelerating RLVR performance.
The paper introduces Reward‑Informed Sparse Autoencoders (RI‑SAEs), which use reinforcement‑learning rewards to curate data for training sparse autoencoders on language‑model activations. On Llama‑3.1‑8B, a sparse subset of features separates high‑reward from low‑reward reasoning continuations, but control experiments show this separation largely reflects solution completeness rather than true reasoning quality. The authors conclude that reward filtering can cheaply reuse RL signals for interpretability, though most of the discovered features capture completion form rather than deep reasoning.
arXiv:2607. 21273v1 Announce Type: new Abstract: Dense per-step supervision is an appealing remedy for sparse-reward, long-horizon LLM agents: reward the agent for predicting its next observation, and memory should follow.
arXiv:2608. 01425v1 Announce Type: cross Abstract: Training LLM-based multi-agent systems with multi-agent reinforcement learning is rapidly gaining traction, and a parallel line of work argues that such systems should be judged by their behavior, not only their reward.
arXiv:2606. 18963v1 Announce Type: new Abstract: We study online reward-punishment learning when the environment provides no scalar reward or evaluative label.
arXiv:2607. 18966v1 Announce Type: new Abstract: Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective.
arXiv:2608. 03223v1 Announce Type: cross Abstract: Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit.
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
arXiv:2606. 00726v1 Announce Type: new Abstract: Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation.