cs.AINov 14, 2026

Continuation-Guided LLM Evolution of Program Policies and Goal Compilers in Craftax

Authors: Víctor Gallego

Organizations: Komorebi AI Technologies

Abstract

Coding agents can synthesize and optimize code-based policies from simulator feedback, allowing the resulting program to act with zero inference model calls. But for long horizon tasks, two challenges arise: local improvements can hurt final success and switching to a new objective requires another expensive synthesis run. We propose a framework that first develops competence by refining the policy through a feedback cascade, moving from episode returns to hierarchical goals and belief updates which can be scored densely from simulator. In the Craftax game, a partially observed and procedurally generated environment, refinements via episode level feedback stall at <1% final-level arrival, whereas with the feedback cascade the optimized policy reaches the final stage 50% of time (28% final boss defeats). Furthermore, to make this competence reusable towards new goals, we factor the previous controller into an environment interpreter II (models, memory, skills) and a rule program p0p_0, and we show that coding agents can optimize a reusable goal compiler CθC_θ that maps structured tasks gg into new rule programs pgp_g. Across five independent compiler searches trained only on short tasks, the resulting compilers successfully transfer zero-shot to longer tasks without any task-specific tuning nor inference-time LLM calls: continuation-scored feedback and a fixed machine with an editable program together turn a single-task competent policy into a reusable one. Code at: https://github.com/vicgalle/craftax-program-policies

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jun 11, 2026

Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents

Code-writing large language models (CodeLLMs) generate executable code policies for embodied agents by translating natural language goals and environmental constraints into structured control programs. However, policy generation in open-domain embodied environments suffers from two fundamental limitations: (i) delayed decoding caused by repetitive prefill computation over long prompts, and (ii) limited robustness due to fully generative decoding, which often produces API mismatches, missing safety guards, and unstable control logic. To address these limitations, we present FCGraft, a Functional Cache Grafting framework. FCGraft maintains a library of function-level validated code skeletons and their associated prompt-level Transformer key-value (KV) caches, and synthesizes new policies by retrieving relevant functions and grafting their KV caches when a new task is provided. Given retrieved function caches, FCGraft performs cache grafting via stitching, which composes cached function segments into a composite policy, and patching, which locally adapts only the necessary code regions to satisfy task-specific parameters and constraints with minimal additional decoding. By eliminating redundant prefill computation, this approach reduces generation latency, while reusing validated control structures improves robustness over prompt-level caching methods RAGCache, achieving 18.31% higher task success rate and 2.3x faster policy synthesis.
Feb 10, 2026

CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs

A core quality of general intelligence is the ability to open-endedly expand and evolve its set of mastered skills autonomously. While recent Foundation Model (FM) driven approaches have shown promising results towards this goal, they typically rely on significant human-in-the-loop engineering, limiting their transferability to novel environments. To address this, we introduce Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs (CODE-SHARP), a framework that leverages FMs to open-endedly grow and evolve an archive of Python programs encoding skills to train a generalist agent policy entirely from scratch via reinforcement learning, directly from source code. These programs, termed Skills as Hierarchical Reward Programs (SHARPs), each encode a local success condition and a set of prerequisites delegated to previously discovered SHARPs. At runtime, SHARPs dynamically route the agent through their prerequisite chain based on the current state, rewarding each completion along the way, requiring the agent to learn only the marginal behaviour each new SHARP introduces, enabling efficient learning of long-horizon skills without any pre-defined rewards. On Craftax-Classic and XLand-MiniGrid, agents trained fully autonomously by CODE-SHARP outperform previous works by 6x and 2.7x in median performance and are the only agents capable of crafting iron tools and mining diamonds. On AI2-THOR, CODE-SHARP achieves 66.7% median success versus 0% for ELLM and OMNI, using only the initial environment state instead of the full source code. Scaled to Craftax-Extended, CODE-SHARP trains a generalist agent on over 90 discovered SHARPs, enabling the agent to solve challenging long-horizon tasks zero-shot, matching agents trained on ground-truth rewards.
Aug 13, 2026

Coding Agents are Strong Prompt Optimizers

Search-based prompt optimizers improve prompts through iterative search: they propose edits, execute fresh rollouts, score the resulting trajectories, and retain only edits that improve a validation metric. We show that this optimization loop is unnecessary. Given only a static corpus of agent trajectories, an off-the-shelf coding agent can directly synthesize an optimized prompt, requiring neither environment access nor validation data. We call this approach Coding-Agent Skill Distillation (CASD). The key insight is reflection scope. Rather than reasoning over a small batch of trajectories at each optimization step, the coding agent writes and executes analysis code to compute corpus-wide statistics, identifies systematic failure modes, inspects representative episodes, and distills the resulting insights into behavioral rules. Across four agentic benchmarks (ALFWorld, τ2τ^2-bench retail and telecom, and SpreadsheetBench-Verified), under matched data access, a single CASD pass outperforms GEPA, a state-of-the-art reflective prompt optimizer, on three of four benchmarks and outperforms validation-gated reflective search (SkillOpt) on all four, improving the unoptimized baseline by 16.6 percentage points on average versus 10.9 for GEPA and 5.3 for SkillOpt. Because CASD performs a single offline analysis pass rather than iterative search, producing an optimized prompt costs approximately $1.60---over 22×22\times cheaper than validation-gated search. Even when competing methods are granted additional validation data and unrestricted environment access, CASD remains ahead on two of four benchmarks. These results suggest that corpus-scale statistical reflection is a viable alternative to iterative search for prompt optimization.