Speculative decoding accelerates LLM inference on SE tasks without accuracy loss, with model-based methods suiting code generation and model-free methods suiting repository-level repair and editing.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.SE 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
LogicLoc combines LLMs with Datalog to achieve accurate repo-level code localization without relying on keyword shortcuts in benchmarks.
SWE-Shepherd trains a lightweight PRM on SWE-Bench trajectories to score intermediate actions and guide code agents, showing gains in efficiency and action quality on SWE-Bench Verified.
citing papers explorer
-
An Empirical Study of Speculative Decoding on Software Engineering Tasks
Speculative decoding accelerates LLM inference on SE tasks without accuracy loss, with model-based methods suiting code generation and model-free methods suiting repository-level repair and editing.
-
Neurosymbolic Repo-level Code Localization
LogicLoc combines LLMs with Datalog to achieve accurate repo-level code localization without relying on keyword shortcuts in benchmarks.
-
SWE-Shepherd: Advancing PRMs for Reinforcing Code Agents
SWE-Shepherd trains a lightweight PRM on SWE-Bench trajectories to score intermediate actions and guide code agents, showing gains in efficiency and action quality on SWE-Bench Verified.