6 papers
Prune the Summary, Not the History: Source-Judged Compaction for Long-Horizon Agents
Guanghui Min, Chen Chen
Long-horizon LLM agents rely on context compaction: when the interaction history outgrows the context window, a compressor replaces it with a natural-language summary. We show that…
Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
Guanghui Min, Liang Wu, Mingjia Shi +4
Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. Existing pr…
MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations
Sky Ng, Brihi Joshi, Ishan Gupta +47
Long-horizon, multi-agent language model (LM) simulations are widely proposed for studying social behavior, yet instruments to measure whether persona-conditioned agents maintain i…
PersonaEval: Persona-Based User Simulation for Evaluating Interactive Applications
Yifan Simon Liu, Qianfeng Wen, Yilan Fan +40
Real user studies are important for understanding how people interact with systems under test or already deployed. In practice, however, they are often costly, time-consuming, and…
Towards Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
Guanghui Min, Liang Wu, Mayank Darbari +2
Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary empirical study, we show that…
SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation
Zaiyi Zheng, Liang Wu, Guanghui Min +4
Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short…