AICoder

AI Coding Live News

First-hand AI coding updates from 𝕏/Twitter frontier labs and researchers, distilled by AI with entity benchmarks.

Explore live on 𝕏 ↗

AI Coding Live News

@
@huggingface@huggingface·
👀100
🔥94

Judge-Free Test-Time Scaling Tops WebArena Infinity at 74.6%: Salesforce Introduces CLIFT, Alongside MMSearch-OPD and SCOPED-8B Beating 32B VLMs

Three new frameworks advance web and multimodal agent post-training: Salesforce AI Research's CLIFT (arXiv:2610.06829) certifies URL-conditional self-verification questions for dense RL rewards and judge-free Conformal Trajectory Selection (CTS), propelling Gemma-4 31B to a 74.6% SOTA on WebArena Infinity (beating Gemini 3 Flash at 70.1%) and lifting GPT-5.5 to 53.7% on VisualWebArena. Meanwhile, MMSearch-OPD (arXiv:2610.22240) boosts 9B multimodal deep search by +15.3 points to 60.2%, and Northeastern University's SCOPED-8B (arXiv:2610.22217) uses skill-decoupled on-policy expert distillation to reach 73.13% across 8 benchmarks—surpassing Qwen3-VL-32B (72.01%) and Claude Opus 4.6 (72.86%).

Judge-Free Test-Time Scaling Tops WebArena Infinity at 74.6%: Salesforce Introduces CLIFT, Alongside MMSearch-OPD and SCOPED-8B Beating 32B VLMs

Key Takeaways

  • Salesforce's CLIFT conformal self-verification propels Gemma-4 31B to 74.6% on WebArena Infinity (+12.8 pts over base, beating Gemini 3 Flash at 70.1%) with judge-free test-time trajectory selection
  • Transferring the open-trained CLIFT question bank to GPT-5.5 sets a 53.7% SOTA on VisualWebArena, while MMSearch-OPD boosts 9B multimodal deep search accuracy by +15.3 points to 60.2%
  • Northeastern University's SCOPED-8B reaches 73.13% average accuracy across 8 VLM benchmarks via skill-decoupled on-policy expert distillation, beating Qwen3-VL-32B (72.01%) and Claude-Opus-4.6 (72.86%)
Read full story
Linked Models & Agents:
#CLIFT#WebArena#VisualWebArena#Salesforce-AI#MMSearch-OPD#SCOPED
H
Hugging Face Daily Papers@HuggingFace·
👀88
🔥98

Web$hell Unifies Agentic Web Access: Bridging Search, Browser Interaction, and File Caching Cuts Deep Research Turns by 66%

As LLM agents are deployed on long-horizon, end-to-end open web tasks such as deep research, multi-vendor comparison, and cross-site navigation, existing web access paradigms suffer severe fragmentation: search-augmented agents discard interactive controls, browser-based agents incur prohibitive context token consumption, and filesystem-based tools (Fetch-then-Explore) lose crucial interaction contexts when selectively grepping text. Researchers from Yonsei University introduce Web$hell (arXiv:2610.13416), a unified interface standardizing web access. Anchored by WebContract (establishing consistent schemas for addresses, values, and associations), WebCompiler (deterministically transforming HTML semantics into operable information and action objects without LLM inference overhead), and WebCache (maintaining persistent, stateful page revision trees), Web$hell unifies passive discovery with active interaction. Evaluated across six benchmarks spanning Web Search (WideSearch, SealQA), Web Navigation (WebArena-Verified, WebWalkerQA), and Deep Research (DeepResearchBench, DeepWeb-Bench), Web$hell achieves state-of-the-art performance across all tasks. Crucially, it slashes Deep Research turns from 52.4 and 30.9 down to 17.6 (-43% to -66%), maintaining flat cost curves even when subjected to 400 injected distractor pages.

Key Takeaways

  • Web$hell unifies web search, interactive navigation, and file caching under a single interface for LLM agents
  • Employs WebContract, deterministic WebCompiler, and stateful WebCache to achieve SOTA across 6 web benchmarks
  • Cuts Deep Research interaction turns from 52.4/30.9 to 17.6 (-66%), demonstrating flat costs under 400 distractor pages
Read full story
Linked Models & Agents:
⚡ Web$hell⚡ GPT-5.6 Luna🤖 Web-Agent🤖 Deep-Research-Agent🌐 Yonsei University🌐 OpenAI🌐 Hugging Face
#Web$hell#Web Agents#Agent-Computer Interface#Deep Research#Web Navigation#Browser Interaction
H
Hugging Face Daily Papers@HuggingFace·
👀97
🔥99

DeskForge: Scalable Dense Supervision from Controllable Desktop Environments Propels Computer-Use Agent Grounding by 11.5%

Computer-use agents face fundamental grounding bottlenecks in real-world desktop environments due to layered windows, shifting layouts, and visually indistinguishable controls. Existing training datasets suffer from sparse labels and static capture conditions. Researchers from ETH Zurich and IBM Research present DeskForge (arXiv:2610.02320), a controllable synthetic desktop environment that orchestrates real-world software across varied window states, themes, and screen resolutions. DeskForge synthesizes dense annotations by fusing desktop screenshots, accessibility trees, and geometric window hierarchies, yielding DeskForge-1M—a corpus of 1.2M observations and 159.7M annotated UI element instances. Fine-tuning vision-language models on 200K DeskForge-1M examples improves zero-shot GUI grounding across five external benchmarks; Qwen3.5-4B gains 11.51 percentage points on ScreenSpot-Pro and 10.11 points on OSWorld-G. In end-to-end task execution, task completions surge from 31 to 50 on WebArena-Infinity and from 3 to 15 on OpenApps. The dataset, models, and code are open-sourced at saidgurbuz.github.io/deskforge.

Key Takeaways

  • ETH Zurich and IBM introduce DeskForge, a controllable environment synthesizing DeskForge-1M with 1.2M observations and 159.7M UI elements
  • Fine-tuning Qwen3.5-4B boosts GUI grounding by 11.51 points on ScreenSpot-Pro and 10.11 points on OSWorld-G across five external benchmarks
  • Multiplies long-horizon task completion: solves 50/119 tasks on WebArena-Infinity (up from 31) and 5x on OpenApps (from 3 to 15), fully open-sourced
Read full story
Linked Models & Agents:
⚡ DeskForge⚡ Qwen3.5-4B⚡ WebArena-Infinity🤖 Computer-Use-Agent🤖 Desktop-Grounding-Agent🤖 GUI-Agent🌐 ETH Zurich🌐 IBM Research🌐 Hugging Face
#DeskForge#Computer Use#GUI Grounding#Desktop Agents#OSWorld#WebArena
H
Hugging Face Daily Papers@HuggingFace·
👀44
🔥97

Tokenizing Reusable Experience: X-Tree Recovers Hierarchical Skill Vocabularies to Boost Autonomous Agent Success by up to 5.8%

Conventional multi-step agents are trained on flat action trajectories, where SFT and RLVR apply uniform loss weights across tokens while ignoring recurring sub-procedures that facilitate top-down hierarchical human reasoning. External skill-retrieval mechanisms fail to bake capabilities into model parameters and falter out-of-domain. Researchers from the University of Waterloo and collaborating institutions introduce X-Tree, an algorithmic framework that tokenizes reusable agent experience analogous to text BPE tokenizers without expensive LLM prompts. By scoring action spans via reusability and compiling canonicalized action flows into a hierarchical eXperience Tree, X-Tree integrates seamlessly into Offline RL, Online RLVR, and On-Policy Self-Distillation, delivering up to a 5.8% task success rate improvement across WebArena, ScienceWorld, and WebShop.

Tokenizing Reusable Experience: X-Tree Recovers Hierarchical Skill Vocabularies to Boost Autonomous Agent Success by up to 5.8%

Key Takeaways

  • Pioneers X-Tree to tokenize reusable experience without external LLM calls, compiling raw traces into hierarchical skill trees
  • Seamlessly augments Offline RL, Online RLVR (adaptive skill bonuses), and on-policy self-distillation
  • Improves task success rates by 4.5% on WebArena, 5.8% on ScienceWorld, and 4.1% on WebShop under identical compute budgets
Read full story
Linked Models & Agents:
⚡ WebArena-Agent⚡ RLVR⚡ ScienceWorld🤖 X-Tree🤖 Skill-Tokenizer🤖 Autonomous-Agent🌐 University of Waterloo🌐 Hugging Face
#X-Tree#Agent Generalization#RLVR#Skill Tokenization#WebArena
ADSponsored
H
Hugging Face Daily Papers@HuggingFace·
👀61
🔥98

X-Tree Tokenizes Reusable Agent Experience: Unsupervised Tree Induction Boosts WebArena Success by 4.5%

Conventional LLM agents treat multi-step trajectories as flat token sequences, applying uniform loss weights and ignoring the hierarchical sub-routines that humans reuse across complex tasks. While prompt-based skills retrieve procedures in-context, they leave model weights unaltered. Inspired by text tokenizers that construct vocabularies through frequency statistics without LLM calls, researchers from Waterloo and UIUC introduce X-Tree. By scoring action-span reusability and merging recurring steps into an eXperience tree, X-Tree integrates into offline RL, online RLVR, and on-policy self-distillation, improving task success by up to 4.5% on WebArena, 5.8% on ScienceWorld, and 4.1% on WebShop.

X-Tree Tokenizes Reusable Agent Experience: Unsupervised Tree Induction Boosts WebArena Success by 4.5%

Key Takeaways

  • Introduces tokenizer-inspired action-stream experience tree induction without any expensive LLM prompting calls
  • Boosts task success rates by 4.5% on WebArena, 5.8% on ScienceWorld, and 4.1% on WebShop at matched compute budgets
  • Seamlessly integrates across offline RL, online RLVR adaptive reward shaping, and on-policy self-distillation
Read full story
Linked Models & Agents:
⚡ Llama-3⚡ Qwen3⚡ WebArena🤖 X-Tree🤖 WebShop🤖 ScienceWorld🌐 Hugging Face🌐 University of Waterloo
#X-Tree#Agent Generalization#Experience Tokenization#RLVR#WebArena
You've caught up with all stories