arXiv:2607. 10139v1 Announce Type: cross Abstract: Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost: self-consistency inherits the errors of the single model it resamples, and trained reward models need labeled data and transfer poorly off-distribution.
The paper proposes treating an ensemble of language models as a jury rather than an electorate, where each model’s reliability is inferred from patterns of agreement and disagreement without using labels. Using Expectation Maximisation, the authors estimate each expert’s latent reliability and derive a log‑odds weighted linear scoring rule. On a 1560‑question benchmark, this label‑free approach matches the performance of label‑fitted weights and surpasses the best single model and other label‑free alternatives.
arXiv:2606.16710v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) are credited with solving complex problems, yet their agents routinely act on context that may be false. Prior work...
The paper introduces Bayesian backward reasoning as a label‑free anchor for multi‑agent collective decision‑making. By constructing reverse posteriors from explicit likelihoods, the authors obtain differently factorized approximations of the underlying posterior, reducing shared errors among agents. Using Jensen‑Shannon divergence to rank agents, they propose three aggregation strategies—hard selection (MinJS), soft reweighting (FwdJS), and log‑linear fusion (LogLin)—which consistently outperform baseline methods on the DDXPlus benchmark across five LLM backbones, especially when agents disagree.
arXiv:2607. 02104v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers.
The paper introduces a method to reduce sycophancy in large language models by using the Bayesian Truth Serum (BTS) as a reward signal in Group Relative Policy Optimization (GRPO). BTS rewards answers that are surprisingly common among a model’s own outputs, eliminating the need for labeled data or preference annotations. Experiments on a true/false benchmark show a significant drop in answer‑flip rates under user pressure and an increase in accuracy, outperforming other reward schemes such as SMART.
The study evaluates multi‑agent debate (MAD) in small language models, testing whether cognitive diversity—via personas, sampling temperature, or model identity—drives performance gains. Across 23 models, five tasks, and over 5,500 runs, MAD consistently outperforms single‑model inference but, when matched for generation budget, it ties or falls behind self‑consistency sampling, with persona prompting actually reducing accuracy. The authors find that MAD’s benefits largely stem from the first answer exchange and that many reported gains are due to ensemble‑sampling effects rather than true diversity, highlighting the need for budget‑matched, contamination‑checked baselines. whyItMatters":"The findings clarify that MAD’s perceived advantages may be overestimated and that future debate mechanisms must be evaluated against rigorous, budget‑matched baselines to ensure genuine performance improvements."
The paper introduces Bayesian Dialectical Argumentation (BDA), a method for aggregating answers from multiple large language models (LLMs) in a council setting. BDA treats each LLM’s typed moves—proposals, challenges, and concessions—as evidence in a classical annotator model, estimating per-agent reliability even when some agents are persistently unreliable. By weighting evidence according to these inferred reliabilities, BDA produces calibrated posterior probabilities for candidate answers and can invert unreliable agents instead of merely outvoting them, achieving superior calibration and robustness on both binary and multi-class benchmarks without extra LLM calls.
The paper introduces a test-time aggregation framework for multi-agent reasoning with large language models. It mitigates non-semantic biases by normalizing reasoning traces and injects bias to create decision instability, which signals reliability. The method improves accuracy and token efficiency on several mathematical reasoning benchmarks without requiring validation data or prior model strength knowledge.
arXiv:2606. 00005v1 Announce Type: new Abstract: We present the Consilium Protocol, a Byzantine Fault Tolerance-derived architecture for structured multi-model AI deliberation that treats inter-model disagreement as epistemic signal rather than error.
The paper introduces TalkMesh, a decentralized network of small language model agents that learn to communicate effectively during inference. Each agent proposes an answer, scores it with a confidence head, and the most confident agent broadcasts a hint; lower‑confidence agents revise their proposals if a new suggestion scores higher. This gossip‑based consensus, trained via group relative policy optimization, enables a mesh of three agents to match the accuracy of majority voting over 32 samples, and scales to larger meshes to significantly boost performance on benchmarks like GSM8K and MATH-500.
The study examines how groups of large language model (LLM) agents handle misinformation when a few adversarial agents inject false claims into a discussion. In experiments with ten agents across six models and three datasets, a single adversarial agent caused 44.8% of benign agents to adopt the false answer, while three adversaries raised this to 60.5%. Interestingly, many benign agents privately held the false answer yet publicly disagreed, indicating hidden belief collapse that is not visible in the discussion itself.