arXiv:2608. 01303v1 Announce Type: new Abstract: Symbolic alpha factor discovery can score a completed expression, but it provides no direct label for the structural decisions that produced it.
arXiv:2606. 29476v1 Announce Type: cross Abstract: Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context.
arXiv:2606. 17199v1 Announce Type: cross Abstract: Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo estimator that avoids vocabulary-wide computation.
arXiv:2606. 03238v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) makes large-scale post-training possible by replacing an underspecified human objective with learned and scalable proxies.
arXiv:2607. 29209v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) scores each token against a stronger teacher for a dense advantage but caps performance at teacher quality and discourages exploration beyond it.
arXiv:2608. 04408v1 Announce Type: cross Abstract: On-policy distillation (OPD) supervises student-visited trajectories, yet divergence-based rules cannot determine whether an erroneous prefix remains correctable.
arXiv:2608. 10905v1 Announce Type: new Abstract: On-policy distillation (OPD) applies token-level teacher supervision to student-generated trajectories, but this supervision is not always reliable.
arXiv:2606. 12634v1 Announce Type: cross Abstract: Long-horizon tool-use reinforcement learning can learn from outcome verification, but its trajectory-level advantage is broadcast across many reasoning, API, and answer tokens.
arXiv:2608. 06861v1 Announce Type: new Abstract: Training large language model agents in long-horizon environments requires assigning credit from sparse terminal outcomes to individual actions.
arXiv:2606. 18963v1 Announce Type: new Abstract: We study online reward-punishment learning when the environment provides no scalar reward or evaluative label.
arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.
arXiv:2606. 19236v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from policy entropy collapse during training.
arXiv:2604. 10688v2 Announce Type: replace-cross Abstract: On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit assignment notoriously difficult.