arXiv Machine Learning
Jun 9
Stabilizing On-Policy Distillation for MLLM Reasoning with Global Normalization
arXiv:2606. 09091v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an important post-training paradigm.
Reinforcement learning
Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv AI
Jun 9
An Information-Theoretic Definition for Open-Ended Learning
arXiv:2606. 08369v1 Announce Type: cross Abstract: A growing body of work points to the great promise of AI systems that can continually expand their capabilities as they operate in an open-ended environment.
arXiv AI
Jun 9
LogNEO: A GPT-Neo Reinforcement Learning Framework for Accurate Real-Time Log Anomaly Detection
arXiv:2606. 08153v1 Announce Type: cross Abstract: Detecting anomalies in large-scale system logs is critical for the reliability and security of modern computing infrastructure.
arXiv AI
Jun 9
PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR
arXiv:2606. 08543v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning but often suffers from rapid policy-entropy collapse, where the policy prematurely concentrates on narrow high-probability reasoning paths.
arXiv Machine Learning
Jun 9
PriFT: Prior-Support Guided Supervised Fine-Tuning
arXiv:2606. 09396v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement learning (RL), but it can show weaker generalization than RL.
arXiv AI
Jun 9
A Regret Minimization Framework on Preference Learning in Large Language Models
arXiv:2606. 09124v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provide automated correctness signals.
arXiv Machine Learning
Jun 9
TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles
arXiv:2606. 07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.
arXiv AI
Jun 9
sGPO: Trading Inference FLOPs for Training Efficiency in RLVR
arXiv:2606. 08854v1 Announce Type: cross Abstract: Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each query's difficulty means for the current policy.
arXiv AI
Jun 9
Knowledge Graphs and Reasoning LLMs for Finding Simple Yet Effective Transcriptomic Perturbation Predictors
arXiv:2606. 08816v1 Announce Type: cross Abstract: Predicting the effect of an unseen gene knockout perturbation on transcriptomic gene expression remains a highly challenging problem for virtual cell models.
arXiv AI
Jun 9
The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
arXiv:2601. 15165v4 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders.
arXiv Machine Learning
Jun 9
Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking
arXiv:2606. 08253v1 Announce Type: cross Abstract: Enabling humanoid robots to operate in complex, dynamic environments remains a critical challenge, fundamentally limited by the ability to navigate robustly, safely, and accurately.
arXiv AI
Jun 9
From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
arXiv:2603. 03292v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.
arXiv Machine Learning
Jun 9
Variational Proximal Policy Optimization
arXiv:2606. 08032v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback via Proximal Policy Optimization often suffers from policy mode collapse, brittle exploration loops, and distribution drift.
arXiv Machine Learning
Jun 9
Enhancing Spatial Reasoning in Large Language Models for Metal-Organic Frameworks Structure Prediction
arXiv:2601. 09285v2 Announce Type: replace Abstract: Metal-organic frameworks (MOFs) are porous crystalline materials with broad applications such as carbon capture and drug delivery, yet accurately predicting their 3D structures remains a significant challenge.
arXiv AI
Jun 9
Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents
arXiv:2606. 08875v1 Announce Type: new Abstract: Optimizing large language models (LLMs) for long-horizon caregiver agents requires balancing delayed task objectives with immediate environment dynamics, such as patient distress and resistance.
arXiv AI
Jun 9
Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care
arXiv:2606. 08982v1 Announce Type: new Abstract: Baichuan-M4 is Baichuan Intelligence's clinical-grade medical large model, designed for \emph{continuous care} rather than single-turn medical question answering.
arXiv AI
Jun 9
Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning
arXiv:2606. 08735v1 Announce Type: new Abstract: Quality-diversity reinforcement learning (QD-RL) aims to construct policy repertoires that contain both high-performing and behaviorally diverse policies.
arXiv AI
Jun 9
Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning
arXiv:2606. 07602v1 Announce Type: cross Abstract: LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility.
arXiv AI
Jun 9
Evaluating AI Investment Strategies
arXiv:2606. 08791v1 Announce Type: cross Abstract: We study the problem of auditing a black-box algorithmic decision-maker from observable inputs and outputs alone.
arXiv AI
Jun 9
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs
arXiv:2606. 09038v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories.