Presents TRUST-Bench benchmark for hidden-trigger tool compromises in LLM agents and VISTA-Guard framework for trajectory-aware risk scoring of final actions under untrusted feedback.
Reason- ing with language model is planning with world model
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Alice uses preservation conflicts from failed candidate updates to create class-stratified hypotheses and guide exploration, improving executable world-model learning under prior misalignment.
ReBel uses belief-consistency supervision and belief-aware grouping to improve credit assignment in long-horizon RL for LLM agents, achieving up to 20.4 percentage points higher success and 2.1x better sample efficiency than GRPO on ALFWorld and WebShop.
citing papers explorer
-
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback
Presents TRUST-Bench benchmark for hidden-trigger tool compromises in LLM agents and VISTA-Guard framework for trajectory-aware risk scoring of final actions under untrusted feedback.
-
Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models
Alice uses preservation conflicts from failed candidate updates to create class-stratified hypotheses and guide exploration, improving executable world-model learning under prior misalignment.
-
Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
ReBel uses belief-consistency supervision and belief-aware grouping to improve credit assignment in long-horizon RL for LLM agents, achieving up to 20.4 percentage points higher success and 2.1x better sample efficiency than GRPO on ALFWorld and WebShop.