6 papers · 1 filter
EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents
Xuying Ning, Dongqi Fu, Tianxin Wei +13
Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.…
OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
Yuhang Zhou, Lizhu Zhang, Yifan Wu +5
On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitigating both the off-policy dist…
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Ruizhong Qiu, Hanqing Zeng, Yinglong Xia +15
Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRA…
EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization
Kevin Han, Yuhang Zhou, Mingze Gao +6
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing the reasoning capabilities of Large Language Models (LLMs). However, dominant approaches li…
Exploring System 1 and 2 communication for latent reasoning in LLMs
Julian Coda-Forno, Zhuokai Zhao, Qiang Zhang +6
Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base…
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
Chaoqi Wang, Zhuokai Zhao, Yibo Jiang +8
Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been…