Bayesian-Agent: Posterior-Guided Skill Evolution Across LLM Agent Harnesses

arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these assets through heuristic reflection or raw success counts. Such updates are brittle when trajectories are sparse, expensive, and context-dependent. We introduce Bayesian-Agent, a native and cross-harness framework that treats reusable agent skills as Bayesian evidence objects. Bayesian-Agent records verified trajectories, maintains posterior beliefs over skill reliability and failure modes, and turns those beliefs into auditable skill actions and model-facing guardrails. This posterior view provides a finite-sample alternative to raw empirical-rate skill updates and frames prompt, context, and harness engineering as inference over the external decision environment. On RealFin-Bench, Bayesian skill evolution matches or improves the raw empirical-rate control and yields large gains on native runs. In the incremental mode, incremental repair improves SOP-Bench from 80% to 95%, Lifelong AgentBench from 90% to 100%, and RealFin-Bench from 45% to 65%. Backend and model-scaling ablations further show that posterior-guided repair can operate across BA native, MiniSWEAgent, and Claude Code, provided the harness produces verifiable task artifacts. The source code is available at https://github.com/DataArcTech/Bayesian-Agent.

Related

• Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
• Tree-of-Experience: A Structured Experience-Management Solution for Self-Evolving Agents under Low-Repetition and Implicit-Reward Environments
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
• SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

Source: arXiv cs.CL | 2026-08-12