10 papers
GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning
Xiang Cheng, Yulan Hu, Lulu Zheng +3
Travel planning in the real world is overwhelmingly a \textit{group} activity, yet existing LLM travel-planning benchmarks reduce it to a single user, where the field is approachin…
Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation
Lulu Zheng, Wenjin Yang, Xiangwen Zhang +4
Multi-stakeholder tasks require one output to satisfy users with conflicting preferences. Holistic LLM judges conflate utility estimation and utility aggregation, yielding unstable…
TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
Jiaxuan Wang, Xuan Ouyang, Zhiyu Chen +4
On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged context. We find that when…
Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling
Jiaxuan Wang, Yulan Hu, Wenjin Yang +3
In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As Large Language Models evolve in…
Beyond ESG Scores: Learning Dynamic Constraints for Sequential Portfolio Optimization
Xin Li, Yan Ke, Longbing Cao
ESG-aware portfolio optimization is increasingly important for sustainable capital allocation, yet most learning-based methods still operationalize ESG by appending static scores t…
The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs
Xin Li, Hao Jiang, Annan Wang +2
On-policy distillation (OPD) is widely used for LLM post-training. When pushed with a reward-extrapolation coefficient lambda > 1, the student can lift past the teacher in domain,…