Episode
Harnessing LLM Agents with Skill Programs
- Podcast
- Daily Paper Cast
- Published
- May 21, 2026
- Duration seconds
- 1320
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/102f0911
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/harnessing-llm-agents-with-skill-programs/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/harnessing-llm-agents-with-skill-programs.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 29 | cs.AI Authors: Hongjun Liu, Yifei Ming, Shafiq Joty, Chen Zhao Title: Harnessing LLM Agents with Skill Programs Arxiv: http://arxiv.org/abs/2605.17734v1 Abstract: Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lessons are often encoded as textual guidance that remains largely advisory, lacking explicit mechanisms for when and how to intervene in the agent loop. To bridge the gap, we introduce HASP(Harnessing LLM Agents with Skill Programs), a new framework that upgrades skills into executable Program Functions (PFs). Rather than offering passive advice, PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context. HASP is highly modular: it can be applied at inference time for direct agent-loop intervention, during post-training to provide structured supervision, or for self-improvement by evolving validated, teacher-reviewed PFs. Empirically, HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks. For example, on web-search reasoning, inference-time PFs alone improve the average performance by 25% compared to (multi-loop) ReAct Agent, while post-training and controlled evolution achieve a 30.4% gain over Search-R1. To provide deeper insights into HASP, our mechanism analysis reveals how PFs trigger and intervene, how skills are internalized, and the requirement for stable skill library evolution.