3 papers
cs.CL2026
LHAW: Controllable Underspecification for Long-Horizon Tasks
George Pu, Michael S. Lee, Udari Madhushani Sehwag +6
Long-horizon workflow agents that operate effectively over extended periods are essential for truly autonomous systems. Their reliable execution critically depends on the ability t…
cs.LG2026
Agentic Rubrics as Contextual Verifiers for SWE Agents
Mohit Raghavendra, Anisha Gunjal, Bing Liu +1
Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite it…
cs.LG2025
Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning
Mohit Raghavendra, Junmo Kang, Alan Ritter
Post-training of Large Language Models often involves a pipeline of Supervised Finetuning (SFT) followed by Preference Finetuning (PFT) using methods like Direct Preference Optimiz…