Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents

About

Reinforcement learning (RL) with outcome-based rewards has achieved significant success in training large language model (LLM) agents for complex reasoning tasks. However, in active reasoning where agents need to strategically ask questions to acquire task-relevant information, we find that LLM agents trained with RL often suffer from information self-locking: the agent ceases to ask informative questions and struggles to internalize already-obtained information. To understand the phenomenon, we decompose active reasoning into two core capabilities: Action Selection (AS), which determines the observation stream through queries, and Belief Tracking (BT), which updates the agent's belief based on collected evidence. We show that deficient AS and BT capabilities will limit the information exploration during RL training. Furthermore, insufficient exploration in turn hinders the improvement of AS and BT, creating a feedback loop that locks the agent in a low-information regime. To resolve the issue, we propose a simple yet effective approach that reallocates the learning signal by injecting easy- to-obtain directional critiques to help the agent escape self-locking. Extensive experiments with 7 datasets show that our approach significantly mitigates the information self-locking, bringing up to 60% improvements.

Deyu Zou, Yongqiang Chen, Fan Feng, Mufei Li, Pan Li, Yu Gong, James Cheng• 2026

Related benchmarks

TaskDatasetResultRank
Preference EstimationPE-GS=2 (test)
Average Outcome Reward54.67
9
Preference EstimationPE GS=3 (test)
Average Outcome Reward80.33
9
Preference EstimationPE-FD=8 (test)
Average Outcome Reward61.28
9
Preference EstimationPE-FD=6 (test)
Average Outcome Reward56.91
9
TroubleshootingFloDial Easy (test)
Average Outcome Reward44.33
9
TroubleshootingFloDial Hard (test)
Average Outcome Reward49
9
Medical DiagnosisMediQ (test)
Average Outcome Reward71.75
9
Showing 7 of 7 rows

Other info

Follow for update