Skip to main content
Search

Alberta Machine Intelligence Institute

2 related articles

Subscribe to updates
  1. arXiv

    RucTangle splits coding-agent patches into commit histories that stay runnable at every commit and lifts pass@1 by 16.6% on average in regression repair

    The work introduces RucTangle, an agentic commit-untangling method that groups a patch's changes by development purpose, orders them, applies each commit and checks whether the code still runs, revising order first, then regrouping via the agent, and finally merging adjacent commits while preserving the patch's final code; on 131 agent-generated patches it is the only method that reconstructs every patch with all commits runnable, at a median of eight commits, whereas baselines leave 20.6%–37.4% of histories with at least one unrunnable version. The authors also present TangleEval, which has two coding agents repair 453 regression-introducing patches; adding RucTangle histories plus git bisect results raises pass@1 from 26.9% to 31.3% and from 30.8% to 36.0%.

  2. arXiv

    Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis

    This work first shows through controlled experiments on PRMBench and ROSCOE that supplying the correct answer does not consistently improve reasoning quality, locating the flaws in the structure of reasoning traces rather than in answer awareness, and then proposes CRAFT: it rolls out K candidate traces per sample, extracts consensus terms via TF-IRF and filters steps by z-score, converts each trace into a Reasoning Knowledge Graph with steps as nodes and logical relations as edges, aggregates them into a consensus graph, and synthesizes one new trace by traversing that graph in topological order; across FLD, FOLIO, GSM8K and OlympiadBench with GPT-5.

You’re all caught up