11 papers
Learning to Optimize through Solver-Grounded Self-Play
Xia Jiang, Yaoxin Wu, Chenyu Zhou +3
Optimization modeling is central to many decision-making scenarios, but traditionally requires extensive domain expertise. While Large Language Models (LLMs) have shown promise in…
Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models
Rui Zhu, Minglong Cao, Chenyu Zhou +2
Modern large language models (LLMs) can translate natural-language descriptions into operations research (OR) formulations. Post-training techniques including reinforcement learnin…
Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization
Sihan Ge, Yichen Lin, Chenyu Zhou +3
Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descriptions, yet realistic operations research (OR) requests are…
SiLR: Structure-Preserving Admission and Process Reward for LLM Tool Agents
Chenyu Zhou, Qiliang Jiang, Shuning Wu +1
A runtime gate for an LLM tool agent is usually cast as a filter. In a ReAct loop a rejected proposal is followed by another at the same state, so the gate is a search operator ove…
Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment
Chenyu Zhou, Qiliang Jiang, Shuning Wu +1
Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal verifiable reward, per-turn methods localize credit onto the turns that mattere…
Multilingual Verifier Bias in RLVR: Benchmark, Rollout Diagnosis, and the Cross-Lingual Selection Bottleneck
Chenyu Zhou, Qiliang Jiang, Xu Zhou
Reinforcement learning with verifiable rewards (RLVR) is a standard recipe for training large language models on mathematical reasoning, where an answer verifier serves as a langua…
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges
Chenyu Zhou
Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown ans…
Certified Speculative Execution for Untrusted AI Agents
Chenyu Zhou, Qiliang Jiang, Shuning Wu +1
Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM…
The Verifier is the Curriculum: Precision Sets the Return on Search in Code Self-Distillation
Chenyu Zhou, Qiliang Jiang, Shuning Wu +1
Post-training a code generator against a learned judge can optimize proxy features that raise the score without improving the artifact. We study the opposite signal: a deterministi…
Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning
Chenyu Zhou, Qiliang Jiang, Shuning Wu +1
We propose MAST (Mechanism-Aligned Selective Targeting), a mechanism-guided method for unlearning RLVR-induced reasoning with substantially lower collateral damage than standard fu…
The Vision Encoder as a Privacy Boundary: Visual-Token Side Channels in Encoder-Free Vision-Language Models
Chenyu Zhou, Qiliang Jiang, Shuning Wu +1
A vision encoder compresses image pixels into semantic embeddings, implicitly acting as a privacy boundary by preserving semantic content while attenuating pixel-local detail requi…