TL;DR
This proposal develops a structure-aware and planning-based approach to dynamic reordering and introduces a compositional neural encoder that operates directly on BDD structure, enabling the use of deep reinforcement learning to guide reordering decisions.
This thesis proposes a unified two-axis framework that organizes SFT and RL methods along a data axis (off-policy to on-policy) and a loss function axis (positive-only to positive-plus-negative to GRPO) and enables controlled ablations of individual components.
DHRCL decomposes feedback into syntax validation, execution success, unit-test pass rate, and AST-based structural similarity, and organizes these signals through a three-stage Syntax, Execution, Pass&Structural curriculum, and introduces stage-aware probability-based token credit redistribution.
Combinatorial problems appear in numerous industrial applications. A common approach is to formulate these problems as declarative constraint models that can subsequently be compiled to and solved by a range of back-end solvers. Recent work shows that Large Language Models (LLMs) can produce correct models from natural language, but even a correct model can be expensive to solve because performance remains sensitive to modelling choices. In this work, we investigate whether LLMs can automate performance-oriented model reformulation. Inspired by Automatic Heuristic Design (AHD), we use an evolutionary framework in which an LLM proposes candidate reformulations that are verified and benchmarked against the user-defined baseline model. We compare AHD-adapted search strategies that control which prior attempts, instructions, and measured feedback enter each prompt. Existing retention strategies prioritize recency or performance, but do not explicitly diversify the context. To cover this gap, we introduce Profile-Diverse Retention (PDR), which applies Maximal Marginal Relevance (MMR) to instance-level runtime vectors to retain behaviourally diverse attempts. We systematically evaluate the strategies on eight CSPLib problems using validation-based final model selection. The results show that: (i) iterative reformulation can produce substantial held-out speedups; (ii) strategies that keep the retained context diverse outperform those that retain only recent or the fastest attempts; and (iii) validation-based selection improves the held-out speedup of every strategy.
Evolutionary program search guided by Large Language Models (LLMs) has emerged as a powerful paradigm for automated scientific discovery. However, current approaches are fundamentally constrained by three bottlenecks: structurally blind parent selection, sparse whole-program evaluation rewards, and static mutation operators that fail to adapt during search. We present GAE (Graph-Augmented Evolution), a framework that resolves these limitations through a tightly coupled, three-pillar architecture. First, a relational graph neural network (GNN) parses programs into typed computation graphs, producing structure-aware embeddings. Second, an RL-optimized meta-controller leverages these embeddings to replace blind evolutionary sampling with a directed policy, dynamically selecting optimal parents and mutation directions based on reward history. Third, an online GRPO fine-tuning loop continuously updates the LLM mutation operator at test-time using group-normalized evaluation rewards, directly aligning the model's generation distribution with high-fitness structural edits. We evaluate GAE on a challenging scientific discovery task: symbolic regression for complex nonlinear oscillator systems. By transforming stochastic search into a directed, self-improving trajectory, GAE efficiently discovers closed-form physical equations, consistently matching or outperforming static LLM-driven baselines and achieving state-of-the-art out-of-distribution performance.
A small language model is trained via supervised fine-tuning followed by reinforcement learning to jointly perform agent selection and structured parameter generation for downstream tool calls, using a hierarchical reward function grounded in retrieval relevance along with query-agent topic alignment to learn task-dependent agent suitability from retrieval performance.
Group-based reinforcement learning methods for multimodal large language models typically rely on trajectory-level credit assignment that applies a single advantage to all tokens in a response. However, multimodal reasoning involves substantially higher perceptual uncertainty than text-only settings, where the model must repeatedly re-examine visual information to verify intermediate interpretations, and different visual groundings can lead to divergent reasoning paths, making such uniform credit assignment particularly inadequate and causing relative advantages to progressively degenerate toward zero. To address these challenges, we propose Multi-Branch Policy Optimization (MBPO), a tree-based framework that constructs reasoning trees at vision-language decision boundaries, enabling sibling branches to explore diverse visual hypotheses and assigning segment-level credit through branch-relative advantages. We further introduce a temporal replay buffer to reuse informative segments while controlling policy staleness. Experiments on several multimodal reasoning benchmarks show that MBPO outperforms representative baselines, improving both learning signal quality and optimization efficiency. The code is publicly available at https://github.com/ShuaiLyu0110/MBPO.