7 papers · 1 filter
REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces
Yuetian Du, Meng Wang, Yucheng Wang +9
Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents. Distillation and latent commu…
The Illusion of : Evaluating the Breakdown of Counterfactual Reasoning in LLMs
Yucheng Wang, Yuetian Du, Zhengyi Liu +8
Counterfactual reasoning requires models to reason beyond the observed world and explain how altered conditions propagate through downstream consequences. Existing benchmarks large…
MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG
Qiuyi Qi, Tian Liang, Jiamu Wang +7
Agentic retrieval-augmented generation (RAG) requires language models to decide when to continue searching and when to answer. Existing RL-based methods rely on external supervisio…
D2R2: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction
Ninghan Fan, Qi Liu, Xunuo Zhu +9
Predicting single-cell transcriptomic responses to genetic perturbations is central to functional genomics and virtual-cell modeling. Existing approaches, however, typically predic…
LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning
Qiang Zhu, Jiajun Wu, Longyi Wang
Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactio…
STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training
Qiuyi Qi, Tian Liang, Mutian Bao +8
Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on long-horizon tasks. However, sparse and delayed rewards often lead to traject…
CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs
Qiuyi Qi, Jinjian Zhang, Mutian Bao +9
Despite their strong reasoning capabilities and extensive world knowledge, Large Language Models (LLMs) frequently generate plans that violate task constraints, undermining their r…