Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

TOPIC · ENTITY #9365

mathematical reasoning

Related event timeline, sources and context from the news index.

EVENT TIMELINE

5

RESEARCH · 1 SOURCE · arXiv cs.AI

LProp: Propagating Latent Uncertainty for Evidence-Conditioned Belief Revision in LLM Agents

The paper (arXiv:2611.23564v1) introduces Latent Uncertainty, a latent-space estimator, and LProp, a method that revises inherited answer distributions using latent representations plus new evidence without extra trajectory sampling. Evaluated on multiple-choice, yes/no, open-ended QA and mathematical reasoning tasks, the approach outperforms baselines on most metrics and achieves the lowest mean inference-token usage across eight propagation settings.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

DELA: controllable draft-level edits for diffusion language models (arXiv:2610.32096v1)

The paper introduces DELA (Diffusion Editing Language Adapter), a plug-in controller that enables explicit draft-level editing for frozen diffusion language models via four actions (Insert, Delete, Remask, Stop). DELA uses a two-phase decoding scheme—fast append-only drafting that preserves KV-cache reuse followed by global refinement—and a staged curriculum to train the controller; experiments on mathematical reasoning and code generation report up to 5.5 percentage points improvement over direct diffusion decoding.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

CToM: train LLMs to anticipate user responses and self-revise

This arXiv paper proposes Collaborative Theory of Mind (CToM), a framework that trains LLMs to draft a response, predict the user's reply to that draft, and use the predicted reply to guide internal revision before presenting an answer. Combined with group-relative policy optimization (GRPO) and a prediction-based loss, CToM improves collaborative task performance and interaction efficiency across mathematical reasoning, coding, and writing — e.g., raising final accuracy on a collaborative math task from 74.1% to 79.6% versus naive GRPO and reducing user replies by 8% on coding and 17% on writing under equal reward.

7.0

RESEARCH · 1 SOURCE · arXiv cs.AI

SmartSalesBench: a multi-turn benchmark for evaluating LLM sales agents against resistant buyer personas

SmartSalesBench is a newly published benchmark (arXiv:2610.12975v1) that evaluates large language model sales agents in multi-turn (up to 20 turns) conversations against psychologically grounded, resistance‑aware buyer personas. The dataset covers 13,680 sessions across five agent profiles, twelve buyer personas, fifteen smartphone products in six price tiers, uses retrieval‑augmented generation for grounding, and introduces nine evaluation metrics (primary: CR, BRS, RIR) with combined automated LLM‑as‑judge and human (n=50, κ=0.71, Pearson r=0.81 vs BRS) assessment.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

Learning What to Skip (LW2S): counterfactual credit assignment for efficient multi-agent LLM workflows

The paper (arXiv:2609.30734v1) frames omitting components of multi-agent LLM workflows as a counterfactual credit-assignment problem and introduces Learning What to Skip (LW2S). LW2S learns action-specific safety models from controlled skip interventions and uses held-out calibration plus domain-native guards to decide which workflow steps to skip; in evaluations on mathematical reasoning, multiple-choice QA, and code generation with two instruction-model families it reduces recorded token cost while matching or improving full-workflow accuracy in the tested settings.

6.0