TL;DR
The results indicate that, for formal languages with a deterministic semantics, the interpreter itself is sufficient to act as the primary training supervisor.
Narcissus is a synthesizer that keeps the proposals as syntax trees and scores each expansion of a candidate program in its context: does a proposal with the same surrounding structure continue the same way, and does the expansion rebuild a fragment the proposals repeat?
This work evaluates open-source coding LLMs under two semantic formalisms and two semantic shifts across Human-Written, LLM-Translated, and Fuzzer-Generated program splits, showing that LLMs lean on pre-training priors rather than systematically applying the given rules.
ReMCTS, an execution-grounded, memory-augmented, LLM-guided MCTS-style search framework that organizes program candidates as tree states, retains branch-local debugging context, retrieves failure experience across branches, and distinguishes failed checks from unavailable evidence is presented.
Large language models (LLMs) have shown strong performance in static code tasks like code search, summarization, and generation, but remain limited in dynamic code reasoning, which involves inferring how programs behave during execution without actually running them. This limitation stems from LLMs being trained on sta...
WebGrader is proposed, a self-evolving programmatic grader that autonomously derives the required interaction flows from each website request, represents each flow as an executable Flow Contract, and uses its execution outcome as an RL reward.
This work compares a ~28M-parameter autoregressive Tiny Recursive Model (TRM-AR) on natural-language-to-Python code generation against parameter-matched and depth-matched controls, tracking fit and generation across 40 epochs and three seeds.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
