arXiv AI
Aug 6
COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation
arXiv:2608. 04336v1 Announce Type: cross Abstract: Code generation systems make each LLM call with a model, a prompt, and decoding settings.
Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement
Related stories
arXiv AI
Oct 2
Benchmarking Prompt Optimization of Large Language Models With Chess
arXiv:2610. 00416v1 Announce Type: new Abstract: Evaluating large language models becomes increasingly challenging as their capabilities advance: benchmarks can saturate, public test sets risk contamination, and assessing harder tasks can require expensive grading or execution infrastructure.
arXiv Machine Learning
Aug 4
Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training
arXiv:2608. 02391v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive.
arXiv AI
Sep 16
Coaching Qwen3 Coder 30B to Think Like a CodeClash Arena Agent
arXiv:2609.16096v1 Announce Type: cross Abstract: Large language model coding agents have recently become useful for software tasks, but weaker or open-weight agents still struggle to reliably interp...
arXiv Machine Learning
5d ago
MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization
arXiv:2605.19330v2 Announce Type: replace-cross Abstract: LLM agents organize behavior through skills -- structured natural-language specifications that govern how an agent reasons, retrieves, and re...
arXiv AI
Jul 7
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
arXiv:2607. 03451v1 Announce Type: cross Abstract: While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines.
arXiv AI
Sep 28
Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents
The paper introduces CodeHack, a library of code-based skills with natural-language descriptions designed to improve language agents in complex environments like NetHack. By allowing agents to invoke reusable skills instead of selecting individual actions, the study shows that skill-based agents nearly triple game progression and cut inference cost by 86% in zero‑shot settings, while still retaining the option to fall back on primitive actions. In reinforcement learning, skill-based agents learn faster, achieving a 7.2× larger average gain in dungeon level within the same training budget.
arXiv AI
Aug 7
Recursive Synthesis for Long-Horizon Terminal Tasks
arXiv:2608. 05466v1 Announce Type: new Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instruction, environment, reference solution, and verifier mutually consistent.
arXiv AI
Jun 4
SePO: Self-Evolving Prompt Agent for System Prompt Optimization
arXiv:2606. 04465v1 Announce Type: cross Abstract: System prompt optimization improves agent behavior without modifying the underlying model, yielding human-readable, model-agnostic instructions.
arXiv Machine Learning
Aug 3
Overcoming the Weakest-Link Effect in LLM-Driven Program Optimization via Heterogeneous Edit Recombination
arXiv:2607. 28947v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to solve complex problems by searching over program space, offering a general paradigm for scientific problems that can be naturally represented and solved as programs.
arXiv AI
1d ago
Self-Evolving Coding Agents via Harness-Policy Optimization
arXiv:2610.22791v1 Announce Type: cross Abstract: Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and...
arXiv AI
Jul 29
DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
arXiv:2607. 25675v1 Announce Type: new Abstract: Text-space optimization adapts large language models (LLMs) by editing external natural-language artifacts rather than model weights, so the optimized artifacts remain inspectable and the model can be treated as a black box.