Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Harnessing LLM Agents with Skill Programs

About

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.

Hongjun Liu, Yifei Ming, Shafiq Joty, Chen Zhao• 2026

Related benchmarks

TaskDatasetResultRank
CodingHumanEval+
Pass@185
164
CodingMBPP+
Pass@174
117
Web-search reasoningWeb-search reasoning suite (HotpotQA, 2Wiki, MuSiQue) (test)
Accuracy (HotpotQA)69
18
Mathematical ReasoningMathematical reasoning suite AIME24, AMC23, GameOf24 (test)
AIME24 Accuracy16.7
17
CodingMBPP Base
Pass@192
15
CodingHumanEval, MBPP, BigCodeBench Aggregate
Aggregate Average Score69.9
15
CodingHumanEval Base
Pass@191
15
CodingBigCodeBench Full
pass@150
15
CodingBigCodeBench Hard
Pass@128
15
Showing 9 of 9 rows

Other info

Follow for update