·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Figma announces new features to define how agents work on its platform5h◆Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs6h◆Harness^2: Recursive Agent Harnessing for an Open World6h◆ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI6h◆Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware6h◆SAT-RL: Training Language Models for Logical Reasoning with Symbolic Solvers6h◆Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support6h◆AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decoding-Aligned Prefixes6h◆Narrowing the Collaboration Gap, Probably6h◆Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration6h◆PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation6h◆Learning after Execution with Action-Specific Credit6h◆CB-Agent: Concept-Based In-Context Learning for Sequential Action Selection6h◆Iterate on an LLM, Serve on an SLM6h◆Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning6h◆From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement6h◆PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents6h◆Relational Semantic Grounding for Test-Time Discovery6h◆MHWA: Multi-timescale Hierarchical World-Action Model6h◆WeatherBridge: Forecast-Aware Multi-Source Input Adaptation for Pretrained Weather Forecasting Models6h◆Figma announces new features to define how agents work on its platform5h◆Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs6h◆Harness^2: Recursive Agent Harnessing for an Open World6h◆ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI6h◆Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware6h◆SAT-RL: Training Language Models for Logical Reasoning with Symbolic Solvers6h◆Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support6h◆AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decoding-Aligned Prefixes6h◆Narrowing the Collaboration Gap, Probably6h◆Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration6h◆PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation6h◆Learning after Execution with Action-Specific Credit6h◆CB-Agent: Concept-Based In-Context Learning for Sequential Action Selection6h◆Iterate on an LLM, Serve on an SLM6h◆Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning6h◆From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement6h◆PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents6h◆Relational Semantic Grounding for Test-Time Discovery6h◆MHWA: Multi-timescale Hierarchical World-Action Model6h◆WeatherBridge: Forecast-Aware Multi-Source Input Adaptation for Pretrained Weather Forecasting Models6h◆
News/SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction
arxiv
PublishedOctober 9, 2026 at 4:00 AM

SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction

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

arXiv:2610.11559v1 Announce Type: cross Abstract: Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use, particularly in task horizon and interaction length. Code assistants require completing long chains

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

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

Your email is used only to send The Bubble Brief. Privacy policy

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
arxivShould SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs6harxivHarness^2: Recursive Agent Harnessing for an Open World6harxivANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI6harxivMeasuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware6h
The Bubble Brief
MON · WED · FRI

Read AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

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

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews