arXiv:2606. 10296v1 Announce Type: cross Abstract: Multi-agent debate systems are typically evaluated only on whether the final answer is correct, overlooking the quality of the intermediate reasoning that debate is designed to produce.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
Evaluating reasoning quality in multi-agent LLM systems is challenging, especially for open-ended tasks without reference answers. We investigate whether intrinsic confidence signals, token-level log-probabilities from decoding, can predict reasoning quality as assessed by LLM-as-judge evaluation.
arXiv:2608. 12877v1 Announce Type: new Abstract: Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains highly challenging.
arXiv:2606. 13591v1 Announce Type: new Abstract: Confidence is used for reliability, oversight, and a range of downstream decision tasks in Natural Language Processing (NLP), yet no existing method produces or evaluates a confidence for the output of a multiagent system.
arXiv:2601. 19921v2 Announce Type: replace-cross Abstract: Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows that vanilla MAD often underperforms simple majority vote despite higher computational cost.
arXiv:2605. 24661v2 Announce Type: replace Abstract: LLMs have achieved remarkable success in complex reasoning tasks, yet current evaluation approaches predominantly rely on final-answer correctness, offering limited insight into the underlying reasoning processes that produce those answers.
arXiv:2606. 22737v2 Announce Type: replace Abstract: Before letting an agent operate over real context, can you prove it used the right evidence?