AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

Cycle-of-Science: Reliable Reasoning through Counterfactual Verification for Agent Decision Making

Ruojie Zhang, Wencheng Zhu, Peiyuan Jiang, dayong zhu

ICML 2026 · Multi-agent systems and games › LLM agents · approach: Self-evolving language agent learning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Cycle-of-Science, a scientific-method-inspired framework where LLM agents autonomously explore potential causal relationships to improve decision-making reliability via counterfactual verification.

Problem

LLM agents learn passively from similar past experiences, which confounds correlation with causality and hurts robust decision-making.

Approach

Inspired by the Scientific Method, the agent cycles through exploring potential causal relations and verifying them through counterfactual checks, rather than learning passively from similar experiences.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the Hypothesis-Experiment-Validation scientific loop (SFT+CPO) (ablation)CoS Mistral-7B · ScienceWorld (unseen)success rate (%): 56.41 -> 67.23Improved
add the scientific loop (SFT+CPO) (ablation)CoS Llama-3-8B · ScienceWorld (unseen)success rate (%): 55.23 -> 65.35Improved
add the scientific loop (SFT+CPO) (ablation)CoS Gemma-7B · ScienceWorld (unseen)success rate (%): 51.17 -> 60.47Improved
add CPO after SFT instead of SFT only (ablation)CoS Mistral-7B · ScienceWorld (unseen)success rate (%): 62.34 -> 67.23Improved
use CPO only instead of SFT only (ablation)CoS Mistral-7B · ScienceWorld (unseen)success rate (%): 62.34 -> 65.18Improved
increase hypotheses from N=1 to N=3 (ablation)CoS Mistral-7B · ScienceWorld (unseen)success rate (%): 58.47 -> 67.23Improved
increase hypotheses from N=3 to N=5 (ablation)CoS Mistral-7B · ScienceWorld (unseen)success rate (%): 67.23 -> 65.74Hurt
use adaptive threshold instead of best fixed threshold delta=0.5 (ablation)CoS Mistral-7B · ScienceWorld (unseen)success rate (%): 65.20 -> 67.23Improved
add intervention-validation filtering (vs no filtering) (ablation)CoS Mistral-7B · ScienceWorld (unseen)success rate (%): 59.34 -> 67.23Improved
raise fixed threshold from 0.3 to 0.7 (ablation)CoS Mistral-7B · ScienceWorld (unseen)success rate (%): 65.47 -> 62.48Hurt
add self-play trajectories (5K human only to 1:9 mix, 50K total) (ablation)CoS · ALFWorldsuccess rate (%): 72.18 -> 80.51Improved
increase self-play data from 1:9 to 1:19 (ablation)CoS · ALFWorldsuccess rate (%): 80.51 -> 79.94No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy