7 papers
MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning
Yixuan Xie, Xueqiang Xu, Xinyi Fan +8
Agent memory enables large language model (LLM) agents to reuse past experiences without updating their parameters. However, semantic similarity alone does not guarantee memory use…
PB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO
Jingquan Wang, Jun Yin, Xu Han +3
Building LLMs that behave well socially, not merely correctly, requires Building LLMs that behave well socially, not merely correctly, requires more than producing locally helpful…
HyperMCTS: Hypergraph-Augmented MCTS for Long-Horizon LLM Agents
Tingsong Xiao, Nithish Balachandar Moudhgalya, Chandrayee Basu +5
Long-horizon tasks require large language model (LLM) agents to coordinate decisions under constraints that span an entire solution. Monte Carlo Tree Search (MCTS) offers a promisi…
Cliff: Learning Process Rewards from the First Mistake
Peixuan Han, Runhui Wang, Ketan Ramaneti +3
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for large language model (LLM) post-training, but its reliance on coarse outcome rewards le…
GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules
Houde Dong, Yifei She, Kai Ye +3
Online content moderation is essential for maintaining a healthy digital environment, and reliance on AI for this task continues to grow. Consider a user comment using national ste…
Beyond Perfect APIs: A Comprehensive Evaluation of LLM Agents Under Real-World API Complexity
Doyoung Kim, Zhiwei Ren, Jie Hao +11
We introduce WildAGTEval, a benchmark designed to evaluate large language model (LLM) agents' function-calling capabilities under realistic API complexity. Unlike prior work that a…
STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question Answering
Zhenyu Bi, Daniel Hajialigol, Zhongkai Sun +2
Multi-hop question answering (MHQA) requires a model to retrieve and integrate information from multiple passages to answer a complex question. Recent systems leverage the power of…