Right Answers, Wrong Habits: Selecting Self-Generated Agent Trajectories by Evidence Sufficiency

Tool-using agents are routinely improved by fine-tuning on their own successful trajectories, and “successful” almost always means that the final answer was correct. But a correct answer need not be justified by what the agent observed. On a closed-world ProofWriter tool-use task, a sound checker certifies that the observed evidence determines the answer in only about one in seven of a 4B agent’s correct trajectories, and 316 of 877 outcome-selected training trajectories submit before observing anything. Fine-tuning the agent on them barely helps: the student often answers without looking and scores below an agent that gives the same answer to every question. We instead keep a correct trajectory only if a deterministic evidence-sufficiency certificate, which replays the agent’s tool calls, shows that the observed replies determine the answer under the declared semantics. With the same model, trajectory source, episode count and update count, certificate selection lifts macro accuracy from 39.7% to 59.3% (+19.6 points, 95% CI [18.4, 20.8], positive in all five seeds; our pre-specified primary contrast) and beats a length control, an observation-ratio heuristic and an LLM judge; against a judge told the task’s semantics the comparison is inconclusive. The advantage replicates in smaller and larger students of the same family (+22.4 and +28.7 points) and, more weakly, in a second model family (+4.4 points, 95% CI [3.0, 5.8]). Students remain weak on question types their teacher never certified, and all results come from one synthetic benchmark.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-16
DOI
https://doi.org/10.5281/zenodo.24268064
Primary Topic
AI-based Problem Solving and Planning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Right Answers, Wrong Habits: Selecting Self-Generated Agent Trajectories by Evidence Sufficiency

Song Xu
1 links
Zenodo (CERN European Organization for Nuclear Research)
AI-based Problem Solving and Planning
preprint

Right Answers, Wrong Habits: Selecting Self-Generated Agent Trajectories by Evidence Sufficiency

Song Xu
preprint en

Abstract

Tool-using agents are routinely improved by fine-tuning on their own successful trajectories, and “successful” almost always means that the final answer was correct. But a correct answer need not be justified by what the agent observed. On a closed-world ProofWriter tool-use task, a sound checker certifies that the observed evidence determines the answer in only about one in seven of a 4B agent’s correct trajectories, and 316 of 877 outcome-selected training trajectories submit before observing anything. Fine-tuning the agent on them barely helps: the student often answers without looking and scores below an agent that gives the same answer to every question. We instead keep a correct trajectory only if a deterministic evidence-sufficiency certificate, which replays the agent’s tool calls, shows that the observed replies determine the answer under the declared semantics. With the same model, trajectory source, episode count and update count, certificate selection lifts macro accuracy from 39.7% to 59.3% (+19.6 points, 95% CI [18.4, 20.8], positive in all five seeds; our pre-specified primary contrast) and beats a length control, an observation-ratio heuristic and an LLM judge; against a judge told the task’s semantics the comparison is inconclusive. The advantage replicates in smaller and larger students of the same family (+22.4 and +28.7 points) and, more weakly, in a second model family (+4.4 points, 95% CI [3.0, 5.8]). Students remain weak on question types their teacher never certified, and all results come from one synthetic benchmark.

Zenodo (CERN European Organization for Nuclear Research)
University of Electronic Science and Technology of China (CN)
Quality education
AI-based Problem Solving and Planning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon