5 papers
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
Md Nayem Uddin, Amir Saeidi, Eduardo Blanco +1
Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relev…
From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
Md Nayem Uddin, Kumar Shubham, Eduardo Blanco +2
Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks p…
GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
Divij Handa, Mihir Parmar, Aswin RRV +3
Repeated Sampling (RS) is a simple inference-time algorithm that has been shown to improve model performance on complex tasks. Although it is an effective way of scaling inference…
ThinkTuning: Instilling Cognitive Reflections without Distillation
Aswin RRV, Jacob Dineen, Divij Handa +4
Recent advances in test-time scaling have led to the emergence of thinking LLMs that exhibit self-reflective behaviors and multi-step reasoning. While RL drives this self-improveme…
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization
Md Nayem Uddin, Amir Saeidi, Divij Handa +5
This paper introduces UnSeenTimeQA, a novel data contamination-free time-sensitive question-answering (TSQA) benchmark. It differs from existing TSQA benchmarks by avoiding web-sea…