·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction4h◆UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering4h◆Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection4h◆INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning4h◆How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution4h◆Trajectory-Level Speculative Decoding for Diffusion Language Models4h◆Below the Noise Floor: Bimodal Seed Collapse and Distinct Failure Modes in Small-Model Knowledge Distillation4h◆Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic Reasoning4h◆Informational Antilocality and the Locality Bias in LLMs4h◆EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion4h◆OpenStamp: A Watermark for Open-Source Language Models4h◆Lexically conditioned realization ambiguity in Korean predicate morphology4h◆QUORUM: QUality-Optimized Routing Using Multiple annotators4h◆Predicting Turn-Taking Outcomes in Multi-Party Conversation: Interpretable Modelling of Speech and Gaze Dynamics with Interpersonal Closeness4h◆When Linguistic and Internal Confidence Diverge in Large Language Models4h◆CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia4h◆A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring4h◆PACE: Publisher-Adaptive Content Extraction via Agentic Automation4h◆Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction4h◆Quantifying Affective Bias in Low-Resource Media: Large-Scale Emotion Profiling of Bengali Headlines4h◆SciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction4h◆UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering4h◆Select, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection4h◆INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning4h◆How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution4h◆Trajectory-Level Speculative Decoding for Diffusion Language Models4h◆Below the Noise Floor: Bimodal Seed Collapse and Distinct Failure Modes in Small-Model Knowledge Distillation4h◆Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic Reasoning4h◆Informational Antilocality and the Locality Bias in LLMs4h◆EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion4h◆OpenStamp: A Watermark for Open-Source Language Models4h◆Lexically conditioned realization ambiguity in Korean predicate morphology4h◆QUORUM: QUality-Optimized Routing Using Multiple annotators4h◆Predicting Turn-Taking Outcomes in Multi-Party Conversation: Interpretable Modelling of Speech and Gaze Dynamics with Interpersonal Closeness4h◆When Linguistic and Internal Confidence Diverge in Large Language Models4h◆CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia4h◆A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring4h◆PACE: Publisher-Adaptive Content Extraction via Agentic Automation4h◆Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction4h◆Quantifying Affective Bias in Low-Resource Media: Large-Scale Emotion Profiling of Bengali Headlines4h◆
News/First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game Agents
arxiv
PublishedAugust 31, 2026 at 4:00 AM

First Make It Playable, Then Make It Good: Staged Interaction Learning for Small Dialogue-Game Agents

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2608.27672v1 Announce Type: new Abstract: We present Qwen-GuidePlay-2B, a 2B-parameter language model for dialogue-game interaction. We fine-tune Qwen3.5-2B using three steps: a) SFT on only successful game trajectories from Playpen, b) weighted turn-level SFT, and c) teacher-guided SFT. The t

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSciReC: Diagnostic Evaluation of Multimodal, Multi-Turn Relational Reasoning with Adaptive Interaction4harxivUIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering4harxivSelect, Don't Train: The Benefits of Modular Entity Disambiguation with LLM-Based Selection4harxivINSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning4h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews