arXiv AI
Jul 31
Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork
arXiv:2607. 27177v1 Announce Type: new Abstract: Effective collaboration with novel and diverse partners is a crucial skill for autonomous agents.
Reinforcement learning
Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv AI
Jul 31
Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning
arXiv:2508. 16129v3 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities with reinforcement learning paradigm.
arXiv Machine Learning
Jul 31
Representation and Invariance in Reinforcement Learning
arXiv:2112. 07752v4 Announce Type: replace-cross Abstract: Researchers have formalized reinforcement learning (RL) in different ways.
Hugging Face Trending Papers
Jul 30
Cybersecurity Detection Classification with Reasoning-enabled Language Models
A major issue in Security Operations Centers (SOCs) is alert fatigue, as the number of detections reported is more than staff can triage in a given day. Prior work prompts or fine-tunes large language models (LLMs) to emit a triage label directly, but does not train them to reason about whether a detection is a genuine threat.
Hugging Face Trending Papers
Jul 30
LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identical rollout rewards consume generation budget without effective learning signals. Pre-rollout prompt selection can reduce this waste by screening prompts before rollout generation.
Hugging Face Trending Papers
Jul 30
Contrastive Reinforced Policy Optimization via Privileged Self-Distillation
Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level supervision, it inherently suffers from exposure bias due to the privileged information of the self-teacher.
Hugging Face Trending Papers
Jul 30
MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation
Credit assignment is a fundamental challenge in cooperative multi-agent reinforcement learning, particularly in embodied AI settings characterized by limited and delayed feedback as well as dynamically changing numbers of active agents. We propose MARS-RA, a framework that reformulates credit assignment as a rank aggregation problem using contribution-based pairwise comparisons among agents generated by large multimodal models.
Hugging Face Trending Papers
Jul 30
Class-Aware Reinforcement Learning for Counterfactual Explanation Generation
Counterfactual explanations (CFEs) enhance the interpretability of black-box models by generating alternative instances with adjusted feature values that achieve a contrastive outcome. Reinforcement learning (RL) offers a promising approach for CFE generation, enabling efficient exploration of counterfactual instances while ensuring control over key metrics like validity, sparsity, and proximity.
Hugging Face Trending Papers
Jul 30
One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting
Scene text spotting requires high-precision alignment between textual recognition and spatial localization. While visual-token grounding has emerged as a promising formulation for Multimodal Large Language Models (MLLMs), the previous multi-patch paradigm often introduces redundant noise and localization ambiguity, particularly for dense or small text instances.
Hugging Face Trending Papers
Jul 30
LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts
Reinforcement learning from verifiable rewards (RLVR) for mathematical reasoning suffers from a structural blind spot: on "cliff" prompts-those on which every sampled rollout in a group fails-the group-normalized advantage is identically zero, so GRPO produces no gradient on precisely the prompts at the frontier of the model's capability. We introduce LoRA Scaffolded Policy Optimization (LSPO), a sampling-time mechanism that recovers this lost gradient.
arXiv Machine Learning
Jul 30
Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
arXiv:2607. 26358v1 Announce Type: new Abstract: Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift from a reference policy.
arXiv Machine Learning
Jul 30
GPT-Red: Automated Red Teaming via Self-Play at Scale
arXiv:2607. 26115v1 Announce Type: cross Abstract: We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs.
arXiv Machine Learning
Jul 30
Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR
arXiv:2607. 26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal.
arXiv Machine Learning
Jul 30
Weak-to-Strong On-Policy Distillation
arXiv:2607. 26246v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabilities across LLMs.
arXiv Machine Learning
Jul 30
Learning Implicit Causal World Models from Multi-Agent Demonstrations
arXiv:2607. 26336v1 Announce Type: new Abstract: In model-based reinforcement learning, world models exist as internal simulators, but their training often conflates statistical correlations with causal mechanisms.
arXiv Machine Learning
Jul 30
Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection
arXiv:2607. 26273v1 Announce Type: new Abstract: We consider a stochastic multi-objective bandit problem where, at each round, the agent selects a slate of $k$ arms and observes their $d$-dimensional reward vectors under semi-bandit feedback.
arXiv Machine Learning
Jul 30
SymmGrid: Super-Scaling On-Robot Learning with Parallelized Symmetries and Egocentric-Exocentric Visual Perception
arXiv:2607. 26985v1 Announce Type: cross Abstract: Deep reinforcement policy learning directly in physical robots (on-robot learning) remains bottlenecked by slow wall-clock training times.
arXiv Machine Learning
Jul 30
Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models
arXiv:2607. 26845v1 Announce Type: new Abstract: Inference-time thinking improves the performance of large language models, but aggregate outcomes do not reveal whether models use available evidence more effectively or seek information that could improve future decisions.
arXiv Machine Learning
Jul 30
Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning
arXiv:2607. 26059v1 Announce Type: new Abstract: We report a striking phenomenon: deep reinforcement learning agents trained with frozen, randomly initialized CNN feature extractors spontaneously develop extremely sparse fully-connected representations, without any sparsity-inducing objective.
arXiv Machine Learning
Jul 30
HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models
arXiv:2607. 26515v1 Announce Type: new Abstract: We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision.