Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
Many critical reasoning tasks, including clinical diagnosis, legal judgment, and industrial fault diagnosis, require step-dependent causal chains in which early errors propagate and correct conclusions can mask invalid reasoning. Although large language models perform well on such tasks, privacy, latency, and controllability motivate distillation into locally deployable models.
Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confounding error, and votes fragment across multiple valid answers, letting an invalid answer win despite a valid minority trace. We introduce CALVER (Causal Axiom-Level VERification), a training-free symbolic verifier that scores structured traces against Pearl's causal criteria, including -separation, backdoor adjustment, and intervention, and selects the highest-scoring candidate without consulting a reference answer.
Historical tool-use trajectories provide valuable experience for large language model (LLM) agents to plan and coordinate tool usage. Existing approaches directly construct tool-level graphs from these trajectories, but the resulting graphs remain tied to specific tools and are hard to generalize across tool sets.
On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this holds, as when the strongest teacher available and the student one wishes to deploy come from different model families, and find that the standard recipes have no answer: teacher latents cannot serve as targets in a foreign coordinate system, per-pixel losses against a teacher that stochastically re-draws local detail degenerate into blur or divergence, and timestep indices lose their meaning across mismatched schedules.
arXiv:2608. 01559v1 Announce Type: cross Abstract: Adversarial self-play is an appealing recipe for legal reasoning: have a student model draft an argument, have an adversary attack it, and reward the student when its argument survives the attack.
arXiv:2608. 02440v1 Announce Type: cross Abstract: In noisy social dilemmas, intended actions are stochastically corrupted before execution, so an observed defection may reflect hostile intent or action error.
arXiv:2506. 22423v2 Announce Type: replace Abstract: Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control.
arXiv:2608. 02509v1 Announce Type: cross Abstract: Sequential decision-making in real-world applications often involves uncertainty about the environment's model.
arXiv:2505. 08630v2 Announce Type: replace Abstract: Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL).
arXiv:2608. 00419v1 Announce Type: new Abstract: Large language models deployed in real-time, regulated settings face knowledge staleness, catastrophic forgetting, hallucination, and weak feedback loops.
arXiv:2608. 02343v1 Announce Type: cross Abstract: Many operational problems are constrained sequential decision processes with large, combinatorial action spaces and interdependent feasibility constraints.
arXiv:2608. 01418v1 Announce Type: cross Abstract: Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models.
arXiv:2512. 09850v2 Announce Type: replace Abstract: We introduce Conformal Bandits, a novel framework integrating Conformal Prediction (CP) into bandit problems, a classic paradigm for sequential decision-making under uncertainty.
arXiv:2608. 02391v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive.
arXiv:2506. 13741v2 Announce Type: replace-cross Abstract: Preference-based reinforcement learning (PbRL) has emerged as a promising approach for learning behaviors from human feedback without predefined reward functions.
arXiv:2604. 10727v2 Announce Type: replace-cross Abstract: Classical information-theoretic learning bounds typically rely on KL mutual information and moment-generating-function (MGF) arguments, which are well matched to bounded or sub-Gaussian losses but can be ineffective when losses or rewards are heavy-tailed.
arXiv:2608. 02302v1 Announce Type: cross Abstract: Long-horizon coding-agent trajectories are poorly matched to the credit units available to train on: a single action has no stable value, an episode label merges productive exploration with abandoned directions, and a fixed window cuts where the logging mechanics fall.
arXiv:2608. 02073v1 Announce Type: cross Abstract: We investigate Optimization under Input Uncertainty (OIU), in which the input to the objective function, rather than the objective function itself, is subject to uncertainty.
arXiv:2608. 02332v1 Announce Type: new Abstract: In offline reinforcement learning (RL), the distribution shift between behavioral data and the learned policy can lead to erroneous \emph{Q}-value estimation, thereby misguiding the direction of policy optimization.
arXiv:2604. 06543v2 Announce Type: replace-cross Abstract: In this work, we demonstrate that reliable stochastic sampling is a fundamental yet unfulfilled requirement for Large Language Models (LLMs) operating as agents.