9 papers
AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents
Zhengkang Guo, Yiyang Li, Lin Qiu +7
As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range inte…
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Xiaohua Wang, Muzhao Tian, Yuqi Zeng +20
Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models…
TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios
Yuanzhe Shen, Zisu Huang, Zhengyuan Wang +14
As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating m…
BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation
Jingwen Xu, Yiyang Lu, Zisu Huang +9
Training LLMs for code-related tasks typically depends on high-quality code-documentation pairs, which are costly to curate and often scarce for niche programming languages. We int…
CSSG: Measuring Code Similarity with Semantic Graphs
Yiyang Lu, Jingwen Xu, Changze Lv +6
Existing code similarity metrics, such as BLEU, CodeBLEU, and TSED, largely rely on surface-level string overlap or abstract syntax tree structures, and often fail to capture deepe…
Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction
Muzhao Tian, Zisu Huang, Xiaohua Wang +8
As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most…