activity
20242026
most citedBeyond Reward Hacking: Causal Rewards for Large Language Model Alignment

1 citations · 1 across the 26 of their papers we have counts for

collaborators
Showing 2026Show all

20 papers · 1 filter

cs.CL2026

CORAL: An LLM-Native Harness for Production Recommender Systems

Muhammad Rafay Azhar, Yuhang Zhou, Gilbert Jiang +7

Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user behavior, and upstream models s…

cs.IR2026

ConnectionMind: Leveraging Social Networks and Large Language Models for Personalized Recommendation at Meta

Haoyu Han, Yuming Liu, Lei Huang +3

Modern recommendation systems on social media platforms such as Meta must model complex social relationships, including friendships, group memberships, and creator interactions, al…

cs.LG2026

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents

Xuying Ning, Dongqi Fu, Tianxin Wei +13

Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.…

cs.CY2026

PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks

Bowen Jiang, Yuan Yuan, Zhuoqun Hao +11

Personal intelligence is becoming a central frontier for user-facing AI agents. To be helpful in everyday life, agents must understand users across the digital contexts where their…

cs.AI2026

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

Yifan Wu, Lizhu Zhang, Yuhang Zhou +5

In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task require…

cs.SE2026

SWE-Together: Evaluating Coding Agents in Interactive User Sessions

Yifan Wu, Zhuokai Zhao, Songlin Li +8

Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is interactive, with us…