37 papers
OpenPM: Auditable Point-in-Time Evaluation for LLM Portfolio-Management Agents
Xinying Cai, Minghao Guo, Jiahe Liu +7
Large language models are increasingly used to read markets, assess risk, and allocate capital. However, reported results for LLM trading agents can be inflated by look-ahead leaka…
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Jiakang Li, Guanyu Zhu, Can Jin +8
Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods often rely on explicit behavio…
Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
Shuhang Lin, Chuhao Zhou, Xiao Lin +5
Knowledge Graph Question Answering (KGQA) offers grounded, interpretable reasoning, but existing methods often fail to provide reliable coverage guarantees over retrieved answers.…
Agent Skill Evaluation and Evolution: Frameworks and Benchmarks
Kexin Ding, Yang Zhou, Can Jin +3
The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ens…
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
Yang Zhou, Zihan Dong, Zhenting Wang +7
Agent skills can remarkably improve task success rates by using human-written procedural documents, but their quality is difficult to assess without environment-grounded verificati…
PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning
Daize Dong, Junlin Chen, Haolong Jia +9
Mixture of Experts (MoE) Large Language Models (LLMs) achieve strong performance at scale. However, reinforcement learning (RL) on MoE-based LLMs often suffers from training instab…