AI Paper Atlas

Research map / Large language models / Agents, code and math

PPDL: LLM-Based Flows as Probabilistic Programs

Louis Mandel, Guillaume Baudart, Mandana Vaziri, Martin Hirzel

ICML 2026 · Large language models › Agents, code and math · approach: Formal verification and proof data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace majority voting with importance sampling over factors (ablation)PPDL code-generation flow · MBPPaccuracy: 69.7% -> 80.5% (granite4-small)Improved
use IS instead of majority voting (ablation)PPDL flow with gpt-oss-120b · LiveCodeBenchaccuracy: 19.5% -> 36.1%Improved
majority voting on LiveCodeBench for gpt-oss models (ablation)gpt-oss-120b · LiveCodeBenchaccuracy: 30.3% -> 19.5%Hurt
IS on LiveCodeBench for gpt-oss-20b (ablation)gpt-oss-20b · LiveCodeBenchaccuracy: 20.8% -> 8.0%Hurt
add inference scaling (IS, 5 particles) with factorsgranite4-small · GSM8kaccuracy: 83.8% -> 93.7%Improved
add inference scaling on strong modelsllama4-maverick · GSM8kaccuracy: 95.3% -> 95.4% (IS)No clear effect
add inference scaling (5 particles) on Fever for llama4-maverickllama4-maverick · Feveraccuracy: 81.6% -> 80.9% (IS)No clear effect
use SMC instead of IS with same particle count (ablation)Rocq theorem-proving agent · MiniF2F-Rocqproblems solved of 244: 87.7 -> 95.0 (40 particles)Improved
increase particles from 5 to 40 in SMC (ablation)Rocq theorem-proving agent · MiniF2F-Rocqproblems solved of 244: 84.7 -> 95.0Improved
SMC vs IS at 5 particles (ablation)Rocq agent · MiniF2F-Rocqproblems solved of 244: 82.7 -> 84.7 (+2.0)Improved
add parallel particles under constant token budget (ablation)Rocq agent · MiniF2F-Rocqproof/repair steps: 74 steps (IS@1) -> 9 steps (SMC@40)Mixed
SMC vs IS on GSM8k granite4-micro (ablation)granite4-micro · GSM8kaccuracy: 87.8% (IS) -> 84.2% (SMC)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy