9 papers
Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
Aswin RRV, Jacob Dineen, Divij Handa +4
The effectiveness of Reinforcement Learning (RL) in Large Language Models (LLMs) depends on the nature and diversity of the data used before and during RL. In particular, reasoning…
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…
When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
Divij Handa, Zehua Zhang, Amir Saeidi +4
Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely…
OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation
Divij Handa, David Blincoe, Orson Adams +1
Deploying capable and user-aligned LLM-based systems necessitates reliable evaluation. While LLMs excel in verifiable tasks like coding and mathematics, where gold-standard solutio…
BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
Zehua Zhang, Ati Priya Bajaj, Divij Handa +13
Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for LLM Agents. Existing methods rely on…
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…