cs.LGOct 30, 2026

Compositional Self-Improvement: Promises and Pitfalls

Authors: Changho Shin, Daiwei Chen, Brenden Lake, Frederic Sala, Ramya Korlakai Vinayak

Organizations: Department of Computer Science, Princeton University, Princeton, NJ · Department of Electrical and Computer Engineering, University of Wisconsin–Madison, Madison, WI · Department of Psychology, Princeton University, Princeton, NJ · Department of Computer Sciences, University of Wisconsin–Madison, Madison, WI

Abstract

Although self-improvement is becoming increasingly important as tasks become more complex, models struggle to generate reliable supervision for harder, out-of-distribution instances. One way to address this challenge is to exploit compositional structure: models often solve simpler subproblems more reliably than full problems, so their subproblem predictions can be composed into supervision for harder ones. We systematically study when this kind of composed supervision supports self-improvement and when it fails. Our controlled experiments identify three failure modes: unreliable subproblem predictions, errors introduced by composition, and limited supervision coverage. Beyond controlled settings, these findings carry over to more realistic coding and reasoning tasks: composed labels are more accurate than direct self-generated labels and improve performance even on compositions longer than those seen during training, while the failure modes remain visible. Further, although these failure modes often keep compositional self-improvement from fully succeeding on its own, a short SFT warmup with compositional self-improvement can bootstrap reinforcement learning on tasks that require composing skills the model already has, particularly when direct exploration rarely succeeds. Together, these findings characterize when compositional self-improvement can provide sufficiently reliable supervision to expand model capabilities.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Mar 23, 2026

Reliable Self-Improvement Training by Verifying Reasoning, Not Just Answers

Self-improvement training, where models learn from self-generated solutions, promises sustained capability gains but suffers from a pervasive failure mode: across multiple rounds, compounding reasoning errors cause accuracy to stall or degrade. We trace this drift to standard filtering criteria that retain solutions based solely on final answer correctness, which lets lucky guesses (correct answers with flawed reasoning) contaminate the training data. We propose Verified Self-Improvement (VSI), a framework that conditions data retention on step-level structural integrity rather than just the final output. VSI validates solutions by recomputing arithmetic steps via a computer-algebra library (sympy), checking intermediate consistency, and enforcing domain constraints. Evaluating VSI on GSM8K with Qwen3-4B-Thinking across 5 rounds of self-improvement against four baselines (no verification, outcome verification, majority voting, and VSI with DPO) shows that VSI rejects approximately 34% of correct-answer solutions, successfully isolating lucky guesses. This cleaner training signal drives sustained accuracy gains across all rounds (80.5% to 91.0%), whereas outcome verification plateaus and unverified training collapses. Finally, converting VSI checks into DPO preference pairs trains the model to distinguish sound reasoning from lucky answers, boosting reward accuracy from 46% to 63%. VSI offers a simple, reproducible recipe for robust self-improvement whenever automated reasoning checks are available.
Nov 8, 2026

Primitives and Paths: Predicting What Post-Training Can Do from What the Base Model Already Has

Does reinforcement learning teach language models new capabilities, or merely amplify ones acquired during pre-training? The literature offers evidence for both: pass@kk studies suggest RL reweights latent behaviours while some controlled composition studies demonstrate gains beyond simple amplification. We argue that this question has no answer independent of the capability state of the base model, and propose a two-dimensional state space for post-trainability. The first axis, effective full-solution support, measures whether successful trajectories can be sampled under a feasible exploration budget. The second axis, atomic primitive coverage, measures whether the constituent skills of a solution can be executed when the burden of composition is removed. Together, these dimensions motivate three regimes -- amplification, composition-limited, and acquisition-limited -- each predicting a distinct empirical signature and calling for a distinct intervention. We propose a prospective measurement protocol and investigate the framework using synthetic composition tasks across three small language models. We find that primitive mastery alone does not guarantee that RL can learn a composition. Checkpoints that execute every primitive reliably can fail to improve when complete solutions are never sampled during training, whereas modest composition supervision that establishes nonzero support enables substantial RL gains. The framework reframes mid-training as preparation for post-training: its role is to move models into states from which RL can operate effectively.
Aug 31, 2026

Evaluating and Improving LLM Self-Modeling

We study self-modeling: an LLM's ability to answer questions about its own behavior. We focus on verifiable behavioral questions, such as whether a prompt edit would change the model's final answer. To measure this capability, we introduce a benchmark that tests diverse types of self-modeling questions. Current models show non-trivial but limited self-modeling skill, and make systematic mistakes on simple counterfactual questions about their own behavior. To improve self-modeling skill, we develop a scalable synthetic-data pipeline that produces self-modeling training data, and show that reinforcement-learning can improve aggregate self-modeling skill across three open-source model families with some transfer to held-out tasks. These gains, however, do not seem to constitute introspection consistently: improved self-modeling may not arise from privileged access to the model's internal decision process.