arXiv:2506. 01623v4 Announce Type: replace Abstract: Humans excel at analogical reasoning - applying knowledge from one task to a related one with minimal relearning.
arXiv:2609.15851v1 Announce Type: new Abstract: Language models can learn from experience, but raw solution trajectories are often too long and noisy to provide effective guidance. In this work, we p...
arXiv:2606. 18132v1 Announce Type: new Abstract: Meta-reinforcement learning enables fast adaptation by extracting shared structure from related tasks, but existing end-to-end methods often couple task inference with embodiment-specific control.
arXiv:2606. 30192v1 Announce Type: new Abstract: Sim-to-real transfer remains a major obstacle for reinforcement learning (RL), especially for vision-based control where image observations exacerbate the state-distribution shift between simulation and the real world.
arXiv:2512. 03438v3 Announce Type: replace Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers.
arXiv:2606. 24601v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) addresses the problem of training multiple agents that pursue collaborative, competitive, or mixed objectives.
arXiv:2609.35942v1 Announce Type: new Abstract: Recent work in visual question answering has shown that vision-language models can exhibit strong reasoning capabilities by translating visual inputs i...
arXiv:2605. 14211v3 Announce Type: replace Abstract: Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales.
arXiv:2607. 12042v1 Announce Type: cross Abstract: Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation.
arXiv:2608. 19669v1 Announce Type: cross Abstract: Latent reasoning has advanced multimodal reasoning through a two-stage training paradigm: (1) a helper image is encoded into latent tokens to teach visual chain-of-thought during a supervised fine-tuning (SFT) stage, and (2) these latent tokens are further refined with reward feedback during a reinforcement learning (RL) stage.
arXiv:2607. 17760v1 Announce Type: cross Abstract: Inverse reinforcement learning (IRL) provides a powerful framework for learning from demonstrations.
The paper investigates how to apply Reinforcement Learning with Verifiable Rewards (RLVR) to large language models across multiple domains. It compares two training paradigms—mixed multi-task RLVR and separate RLVR followed by model merging—using tasks such as math, coding, science, instruction following, and agent. Experiments show that RLVR across domains causes minimal interference and that reasoning-intensive domains can synergize, with insights drawn from information constraints, prediction behavior, and self-verification.
arXiv:2609.14066v1 Announce Type: cross Abstract: Although existing multi-agent Retrieval-Augmented Generation (RAG) systems have demonstrated promise on complex multimodal reasoning tasks, they rema...