14 papers
FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Involving Conflicts
Sizhe Tang, Guangyu Jiang, Yu Li +3
Large Language Models (LLMs) perform strongly on well-specified reasoning tasks with a feasible answer. However, problems encountered in the open world can become ill-posed due to…
Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning
Yu Li, Shu Hong, Tian Lan
Reinforcement learning from verifiable rewards assigns a single scalar to each rollout, leaving token-level credit assignment underspecified in long reasoning traces. On-policy sel…
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition
Yanyu Chen, Jiyue Jiang, Dianzhi Yu +8
The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, m…
IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
Rongqian Chen, Yu Li, Zeyu Fang +3
Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to…
AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery
Yu Li, Chenyang Shao, Xinyang Liu +13
Artificial intelligence research increasingly depends on prolonged cycles of reproduction, debugging, and iterative refinement to achieve State-Of-The-Art (SOTA) performance, creat…
OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
Yu Li, Rui Miao, Tian Lan +1
Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a single trajectory-level advanta…
Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
Yu Li, Sizhe Tang, Tian Lan
Reinforcement learning for Large Language Model agents is often hindered by sparse rewards in multi-step reasoning tasks. Existing approaches like Group Relative Policy Optimizatio…
FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment
Qinhong Lin, Ruitao Feng, Yinglun Feng +7
We study alpha factor mining, the automated discovery of predictive signals from noisy, non-stationary market data-under a practical requirement that mined factors be directly exec…
ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning
Yu Li, Rui Miao, Zhengling Qi +1
The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem inst…
When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO
Yu Li, Tian Lan, Zhengling Qi
Group Relative Policy Optimization (GRPO) has emerged as an effective method for training reasoning models. While it computes advantages based on group mean, GRPO treats each outpu…
DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs
Yu Li, Qiang Hu, Yao Zhang +3
Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent,…
ACDZero: MCTS Agent for Mastering Automated Cyber Defense
Yu Li, Sizhe Tang, Rongqian Chen +5
Automated cyber defense (ACD) seeks to protect computer networks with minimal or no human intervention, reacting to intrusions by taking corrective actions such as isolating hosts,…
InSPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization
Yu Li, Tian Lan, Zhengling Qi
Direct Preference Optimization (DPO) and its variants have become standard for aligning Large Language Models due to their simplicity and offline stability. However, we identify tw…
Voting with the Graph: Stable RLAIF via Topological Consistency Maximization
Boyin Liu, Zhuo Zhang, Sen Huang +8
Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally limited by random measurement er…