# Process-Reward Tactic Evolution for Long-Horizon Bioinformatics Workflows

arXiv: https://arxiv.org/abs/2606.20839 · HTML: https://mlsanity.com/paper/2606.20839/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 16 of 16)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [Memento: Fine-tuning LLM Agents without Fine-tuning LLMs](https://mlsanity.com/paper/2508.16153/) (2025)
- [BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology](https://mlsanity.com/paper/2503.00096/) (2025)
- [Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering](https://mlsanity.com/paper/2604.08224/) (2026)
- [Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills](https://mlsanity.com/paper/2604.05333/) (2026)
- [SkillNet: Create, Evaluate, and Connect AI Skills](https://mlsanity.com/paper/2603.04448/) (2026)
- [Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2604.11753/) (2026)
- [SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents](https://mlsanity.com/paper/2602.12984/) (2026)
- [The Art of Building Verifiers for Computer Use Agents](https://mlsanity.com/paper/2604.06240/) (2026)
- [BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics](https://mlsanity.com/paper/2601.21800/) (2026)
- [WfBench: Automated Generation of Scientific Workflow Benchmarks](https://mlsanity.com/paper/2210.03170/) (2022)
- [Towards LLM-Powered Task-Aware Retrieval of Scientific Workflows for Galaxy](https://mlsanity.com/paper/2511.01757/) (2025)
- [Process Reward Agents for Steering Knowledge-Intensive Reasoning](https://mlsanity.com/paper/2604.09482/) (2026)

## Abstract (arXiv)

LLM agents can write code and call tools, but reliable bioinformatics work requires long-horizon interaction with workflow software, typed data objects, provenance, and biological checks. We study this setting through Galaxy workflow execution. The agent must explore task data, construct or adapt an executable workflow DAG, bind inputs and dataset collections, monitor execution, debug failures, and validate biological outputs. We propose Process-Reward Tactic Evolution, a Galaxy-based training framework that turns verified workflow rollouts into reusable tactics. During training, agents practice on curriculum-organized Galaxy tasks in Agent Gym; process verifiers score workflow construction, software interaction, execution, and biological correctness; successful and failed traces are distilled into a tactic library. At inference, the trained executor, Process-Reward Tactic Evolution, uses this library to execute held-out peer reviewed Galaxy workflow converted BioWorkflow Bench and BioAgent Bench tasks in isolated environments. The paper evaluates whether process-supervised tactic accumulation improves long-horizon bioinformatics workflow completion, biological correctness, and execution efficiency over no-memory and reflection-style baselines.