5 papers
WorkflowArena: Benchmarking Executable Workflow Orchestration in LLM-Based Multi-Agent Systems
Zheng Jiang, Fang Niu, Bo Peng +10
Large language model agents are increasingly deployed as multi-agent systems rather than as a standalone model operating within a single context. Recent agent harnesses allow the m…
Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents
Bofan Xie, Chaokun Wang, Guanchen Ge +4
Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users increasingly ask them to dele…
ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language
Hang Zhang, Chaokun Wang, Yuzhi Pan +12
Large language models (LLMs) have shown strong potential for translating natural-language (NL) requirements into PL/SQL programs, attracting increasing attention from the database…
Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards
Leqi Zheng, Jinbo Su, Fang Niu +8
Reinforcement learning from verifiable rewards (RLVR) drives chain-of-thought reasoning in large language models, yet its binary outcome reward cannot distinguish among correct tra…
SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis
Leqi Zheng, Jinbo Su, Yuying Li +10
Scientific literature synthesis agents increasingly rely on proprietary online services, limiting reproducibility, privacy, and offline deployment. To address this challenge, we in…