12 papers
MetaPS: Adaptive Programmatic Strategy Selection for Market Agents
Jiaxiang Chen, Aotian Luo, Zhouyi Zheng +3
No single market strategy always wins: momentum, mean reversion, risk control,and event-driven rules can each succeed or fail as market conditions change.Rather than asking large l…
Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems
Yiyang Zhao, Zhuo Zhang, Qingxuan Le +2
The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluati…
DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding
Mingxi Zou, Jiaxiang Chen, Junfan Li +4
Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systemati…
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
Mingxi Zou, Zhihan Guo, Langzhang Liang +6
Long-horizon language agents must operate under limited runtime memory, yet existing memory mechanisms often organize experience around descriptive criteria such as relevance, sali…
The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits
Tianhao Cheng, Zeyu Huang, Zihan Qiu +5
A commonly accepted explanation of critic-free RL for LLMs, based on sequence-level rewards, is that it reinforces successful rollouts with a positive advantage while penalizing fa…
CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
Zhuo Wang, Zhuo Zhang, Yafu Li +3
Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation…