Optimizing CLI Agents with Structured Action Credit & Observation
Explore advanced methods to enhance CLI agents using structured action credit and selective observation for improved learning and task execution.
Probabilistic Abductive Commonsense for AI Reasoning
Discover how Probabilistic Abductive Commonsense (PACS) enhances AI reasoning by integrating diverse human beliefs into Large Language Models.
Optimizing AI Allocation Under Aleatoric Uncertainty
Explore optimal AI-driven resource allocation strategies to reduce misallocation caused by aleatoric uncertainty in screening and targeting.
TraceFix: Verified Agent Coordination with TLA+ Counterexamples
Enhance multi-agent coordination protocols with TraceFix, using TLA+ counterexamples for reliable, efficient verification and repair of LLM agent tasks.
AgentEscapeBench: Benchmarking Tool-Grounded Reasoning in LLMs
Discover how AgentEscapeBench evaluates LLM agents' reasoning with external tools in complex, out-of-domain tasks, highlighting key challenges and insights...