CuSearch reallocates rollout budget in RLVR toward deeper-search trajectories as a proxy for retrieval supervision density, yielding up to 11.8 exact-match gains over uniform GRPO sampling on ZeroSearch.
Measuring and narrowing the compositionality gap in language models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
LEAD lets LLMs solve checkers jumping puzzles up to size 13 by using lookahead to recover from irreversible errors on hard steps that break extreme decomposition.
Derives an information-theoretic accuracy upper bound for single-pass LLM multi-hop QA and introduces the InfoQA multi-call framework that improves performance by keeping per-step information load within model capacity.
ECHO stores each agent turn as a source-indexed memory, reconstructs bounded contexts by selecting useful records, and routes RL credit through the same selection trace — reaching 43.4% on BrowseComp-Plus vs 28.9% (GRPO) and 36.1% (SUPO).
Scaling the delegation backbone in hierarchical search agents improves EM by ~11 points while scaling the executor moves EM by only ~2.6 points, and a 1.7B SFT executor matches a frontier sub-agent at 37% fewer tokens.
citing papers explorer
-
CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG
CuSearch reallocates rollout budget in RLVR toward deeper-search trajectories as a proxy for retrieval supervision density, yielding up to 11.8 exact-match gains over uniform GRPO sampling on ZeroSearch.
-
LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning
LEAD lets LLMs solve checkers jumping puzzles up to size 13 by using lookahead to recover from irreversible errors on hard steps that break extreme decomposition.
-
A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA
Derives an information-theoretic accuracy upper bound for single-pass LLM multi-hop QA and introduces the InfoQA multi-call framework that improves performance by keeping per-step information load within model capacity.
-
ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL
ECHO stores each agent turn as a source-indexed memory, reconstructs bounded contexts by selecting useful records, and routes RL credit through the same selection trace — reaching 43.4% on BrowseComp-Plus vs 28.9% (GRPO) and 36.1% (SUPO).
-
Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?
Scaling the delegation backbone in hierarchical search agents improves EM by ~11 points while scaling the executor moves EM by only ~2.6 points, and a 1.7B SFT executor matches a frontier sub-agent at 37% fewer tokens.