Sage, an agentic formalization framework described in arXiv paper 2609.35790v1, suppresses answer leakage to 2.7% while reaching 73.3% pass@4 joint compilation and semantic fidelity on Omni-MATH witho…
A new study on arXiv (2607.15388v1) testing 4,181 Omni-MATH problems with gpt-oss-120b actors finds that broadcast-style peer discussion achieves higher final accuracy than a planner-executor-reviewer…
A new analysis using Item Response Theory (IRT) finds that adding more questions to LLM benchmarks like Omni-MATH yields diminishing returns in measurement precision, because questions on similar topi…
Researchers introduced a controlled student-teacher protocol to study when natural-language feedback improves multi-turn language agent performance beyond repeated attempts. Testing thirteen open-weig…