5 papers
Position: It's Time to Optimize LLMs for Self-Consistency
Itamar Pres, Belinda Z. Li, Laura Ruis +6
Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition on user framing ("sycophancy")…
Vector Policy Optimization: Training for Diversity Improves Test-Time Search
Ryan Bahlous-Boldi, Isha Puri, Idan Shenfeld +6
Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select rollouts with a varie…
Keeping Code-Aware LLMs Fresh: Full Refresh, In-Context Deltas, and Incremental Fine-Tuning
Pradeep Kumar Sharma, Ishaan Puri, Mantinder Jit Singh +2
Modern codebases evolve continuously: files are renamed or deleted; public APIs drift; behavior shifts within otherwise familiar modules. A model trained yesterday to map a develop…
Repository-Aware File Path Retrieval via Fine-Tuned LLMs
Vasudha Yanuganti, Ishaan Puri, Swapnil Chhatre +4
Modern codebases make it hard for developers and AI coding assistants to find the right source files when answering questions like "How does this feature work?" or "Where was the b…
Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods
Isha Puri, Shivchander Sudalairaj, Guangxuan Xu +2
Large language models (LLMs) have achieved significant performance gains via scaling up model sizes and/or data. However, recent evidence suggests diminishing returns from such app…