10 papers
Self-Compacting Language Model Agents
Tianjian Li, Jingyu Zhang, William Jurayj +5
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaf…
Many-Tier Instruction Hierarchy in LLM Agents
Jingyu Zhang, Tianjian Li, William Jurayj +3
Large language model agents receive instructions from many sources-system messages, user prompts, tool outputs, other agents, and more-each carrying different levels of trust and a…
Reasoning over mathematical objects: on-policy reward modeling and test time aggregation
Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim +18
The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must cul…
The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure
Niyati Bafna, Tianjian Li, Kenton Murray +4
Multilingual generation with large language models (LLMs) is often of poor quality for mid- to low-resource languages, but the causes for this are not well-understood. We first dem…
The Flaw of Averages: Quantifying Uniformity of Performance on Benchmarks
Arda Uzunoglu, Tianjian Li, Daniel Khashabi
Benchmarks shape scientific conclusions about model capabilities and steer model development. This creates a feedback loop: stronger benchmarks drive better models, and better mode…
Jointly Reinforcing Diversity and Quality in Language Model Generations
Tianjian Li, Yiming Zhang, Ping Yu +5
Post-training of Large Language Models (LMs) often prioritizes accuracy and helpfulness at the expense of diversity. This creates a tension: while post-training improves response q…