SEAM learns to generate utility-optimized structured experiences via rollouts to boost frozen LLM performance on mathematical reasoning benchmarks with low overhead.
Draw on the executor’s typical strengths and weaknesses to give algorithms, heuristics, and pitfalls that will most help it on future attempts
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
SEAM learns to generate utility-optimized structured experiences via rollouts to boost frozen LLM performance on mathematical reasoning benchmarks with low overhead.