Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2606. 11559v1 Announce Type: new Abstract: Reinforcement learning typically improves multi-turn agent capabilities through the terminal outcome of the trajectories, which makes it difficult to determine credit assignments for each intermediate turns.
arXiv:2511. 07332v2 Announce Type: replace-cross Abstract: Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements.
arXiv:2606. 11284v1 Announce Type: cross Abstract: Real-world multi-agent systems, from traffic coordination to resource allocation, are often modeled as general-sum games where individual incentives conflict with collective welfare.
arXiv:2606. 11324v1 Announce Type: cross Abstract: We introduce Embodied-R1.
arXiv:2606. 11266v1 Announce Type: new Abstract: The cost signal that constrained-RL algorithms optimize against is almost always reactive: the simulator emits a non-zero cost only after a collision has begun, and the Lagrange multiplier of PPO-Lagrangian grows only after the episode budget has been exceeded.
arXiv:2509. 23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences.
arXiv:2606. 12370v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines.
arXiv:2606. 11474v1 Announce Type: new Abstract: In this paper, we study Mahalanobis-guided latent out-of-distribution (OOD) detection for test-time RL controller switching in nonlinear time-varying systems.
arXiv:2606. 11743v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide strong visual, language, and action priors for robot manipulation, but visual observations alone often miss the local contact state required for contact-rich tasks.
arXiv:2606. 11409v1 Announce Type: cross Abstract: Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly.
arXiv:2606. 11798v1 Announce Type: cross Abstract: In this paper, we develop a continuous-time model-free reinforcement learning algorithm to learn deterministic equilibrium policies in general time-inconsistent control problems.
arXiv:2605. 26418v2 Announce Type: replace-cross Abstract: A properly calibrated rule-based autoscaler can beat every one of six mainstream deep reinforcement learning (DRL) algorithms on cost across every workload we test - so when, if ever, does DRL actually help?
arXiv:2606. 11672v1 Announce Type: cross Abstract: This paper explores the value of agentic AI tools for cybersecurity purposes.
Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors. Routes that appear efficient by standard overhead metrics can still lose fidelity when they pass through poorly calibrated couplers.
Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-Token Prediction (MTP) offers a natural solution to accelerate rollouts through speculative decoding, many studies have observed that MTP acceptance rates degrade significantly during RL training, leading to limited speedup performance.
Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training methods largely rely on random masking strategies that overlook intrinsic token dependencies. In this work, we present an empirical analysis of attention in dLLMs and show that tokens attending more strongly to unmasked context exhibit greater generation stability and play a critical role in reasoning.
On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution. However, we show that the learning signal drawn from this distributional gap concentrates on style tokens rather than task-bearing ones, as the hinted model tends to produce more direct, shorter outputs.
arXiv:2606. 09635v1 Announce Type: cross Abstract: Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation.
arXiv:2604. 22565v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts.
arXiv:2606. 10507v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degrades in multi-turn long-horizon agentic tasks.