Long-horizon dialogue agents need to keep user memories stable enough for personalization while adapting when the user genuinely changes. Existing memory systems often append every observation or overwrite old entries by heuristic rules, which makes transient noise hard to distinguish from real belief drift. We introdu...
Jian-Yuan Zhong, Ze-Yu Liu, Ping-Chuan Cao et al.· 0 citations
Long-horizon interactions with LLM-based assistants require memory systems that preserve and update user states, preferences, and interaction histories. Existing evaluations report end-to-end QA accuracy and cannot determine whether errors arise from encoding, retrieval, or generation. We introduce EvalMem, an operatio...
Ze-Yu Liu, Jian-Yuan Zhong, Rong-Duo Han et al.· 0 citations
FinanceHarness is presented, a harness that runs finance-oriented tools and practitioner-guided workflows, automating financial deep research end to end: environment and data construction, the agent execution loop, and reward modeling, and FinanceGym, comprising thesis-driven research questions and rubrics that combine...
Claim-level falsification is proposed as a principle for test-time scaling and instantiated through Claim-Level Reliability Assessment (CLR), a training-free framework that reallocates test-time compute from additional solution sampling to targeted verification.
Sen Xu, Wei Wang, Shixiaoqi Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
