Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2609.34373v2 Announce Type: replace Abstract: Rate-limited multi-agent teams raise three questions the emergent-communication literature has answered only empirically: what an optimal message s...
arXiv:2609.34426v2 Announce Type: replace Abstract: This paper addresses the problem of safe offline reinforcement learning, which involves training a policy to satisfy safety constraints using an of...
arXiv:2604.21863v2 Announce Type: replace-cross Abstract: Deep reinforcement learning for quantum circuit optimization faces three bottlenecks: replay buffers that overlook temporal difference (TD) t...
arXiv:2605.28295v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) trains reasoning models without labeled trajectories, using groups of verifier-scored rollout...
arXiv:2609.33875v2 Announce Type: replace-cross Abstract: Outcome-only reinforcement learning gives software engineering (SWE) agents a terminal success signal but little direct guidance about interm...
arXiv:2609.37085v1 Announce Type: cross Abstract: Data-intensive services in the Computing Continuum must balance analytics quality, resource usage, and cost across heterogeneous nodes with limited a...
arXiv:2609.36572v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further e...
arXiv:2609.35954v1 Announce Type: cross Abstract: Large language model post-training generates self-generated rollouts through reinforcement learning and on-policy distillation, yet this experience i...
Computer use agents (CUAs) have demonstrated strong capabilities in completing digital tasks. However, existing CUAs either rely solely on graphical user interface (GUI) interactions, which are often...
Large language models (LLMs) are increasingly proposed as decision assistants who must reason probabilistically from available evidence under explicit decision costs. We propose a decision-theoretic f...
Reinforcement Learning with Verifiable Rewards (RLVR) methods such as GRPO rely on successful self-generated trajectories, but finite rollout budgets can produce all-fail groups with no reward-based p...
Large generative models can recover realistic detail in real-world video super-resolution (VSR), but processing an entire video with them is computationally expensive. In this work, we present RelayVS...
We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to make unrestricted upd...
An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive agents mainly studies whether...
High-resolution visual question answering often fails because a multimodal model does not acquire the small, spatially localized evidence needed to answer a question. Sequential zooming can recover de...
Recent advances in generative planning have made trajectory inpainting a promising approach to offline goal-conditioned reinforcement learning. However, these methods typically specify the planning ho...
Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the behavior policy can discourage actions having high crit...
Chinese Semantic Error Correction (CSEC) targets semantic errors in Chinese text, which are typically more subtle and complex than spelling and grammatical errors but remain relatively underexplored....
The paper addresses the failure of online conformal prediction when predictions influence actions that determine which outcomes are used for calibration. It introduces Propensity-Weighted Online Conformal Prediction (PW‑OCP), an inverse‑propensity‑weighted recursion that debiases calibration, and a doubly robust variant (DR‑OCP) that further reduces bias. Experiments on synthetic decision tasks, open bandit data, and financial rebalancing demonstrate that PW‑OCP and DR‑OCP improve counterfactual coverage and downstream regret while preserving prediction‑set sharpness.
arXiv:2509. 14952v3 Announce Type: replace Abstract: This paper considers the smooth bilevel optimization in which the lower-level problem is strongly convex and the upper-level problem is possibly nonconvex.