{"slug": "inducing-reasoning-primitives-from-agent-traces", "title": "Inducing Reasoning Primitives from Agent Traces", "summary": "Researchers introduced Reasoning Primitive Induction, a single-pass method that mines successful ReAct agent traces to extract recurrent reasoning moves into a compact library of typed pseudo-tools. The induced libraries outperformed the original agents that generated their traces, achieving gains of up to +44 percentage points on complex reasoning benchmarks. Across five subtasks spanning narrative deduction and constraint-satisfaction planning, the method matched or surpassed expert-authored decompositions while operating at lower inference cost.", "body_md": "arXiv:2606.02994v1 Announce Type: new\nAbstract: ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We introduce Reasoning Primitive Induction, a single-pass method that mines successful ReAct traces, clusters recurrent reasoning moves, and converts the most frequent moves into a compact library of typed pseudo-tools. Each pseudo-tool is specified by a natural-language docstring interpreted by an LLM at invocation time, and a standard ReAct loop composes these primitives at test time. The central result is that induced libraries outperform the very agent that generated their traces: by +44pp on RuleArena NBA (30 -> 74), +30pp on MuSR team allocation (38 -> 68), and +22pp on NatPlan meeting planning (7 -> 29). Across five comparable subtasks spanning narrative deduction, rule application, and constraint-satisfaction planning, a single fixed configuration improves over zero-shot Chain-of-Thought on every subtask, matches or surpasses expert-authored decompositions, and outperforms AWM at lower average inference cost.", "url": "https://wpnews.pro/news/inducing-reasoning-primitives-from-agent-traces", "canonical_source": "https://arxiv.org/abs/2606.02994", "published_at": "2026-06-03 04:00:00+00:00", "updated_at": "2026-06-03 04:18:01.964931+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-agents", "natural-language-processing"], "entities": ["ReAct", "RuleArena", "MuSR", "NatPlan", "Chain-of-Thought", "AWM"], "alternates": {"html": "https://wpnews.pro/news/inducing-reasoning-primitives-from-agent-traces", "markdown": "https://wpnews.pro/news/inducing-reasoning-primitives-from-agent-traces.md", "text": "https://wpnews.pro/news/inducing-reasoning-primitives-from-agent-traces.txt", "jsonld": "https://wpnews.pro/news/inducing-reasoning-primitives-from-agent-traces.jsonld"}}