CLI-Universe synthesizes a verified 6K dataset of terminal-agent tasks that, when used to fine-tune Qwen3-32B, reaches 33.4% on Terminal-Bench 2.0 and sets a new open-source SOTA for models at or below 32B parameters.
hub
Vitabench: Benchmarking llm agents with versatile interactive tasks in real-world applications
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 2
citation-polarity summary
years
2026 15representative citing papers
EComAgentBench is a new benchmark with 662 tasks distributing hidden intent across sources and using source-tagged rubrics, where the strongest of seven tested models reaches only 57.1% accuracy.
SelSkill applies dual-granularity preference learning to selective skill-or-skip decisions, improving task success by 10.9 points and execution precision by 29.1 points on ALFWorld with Qwen3-8B.
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
AgentEscapeBench is a benchmark of 270 tasks across five difficulty tiers that measures LLM agents' ability to manage long-range tool dependencies, state tracking, and intermediate result propagation, revealing sharp performance drops with increasing depth.
MAD-OPD recasts on-policy distillation teachers as a debating collective to supply better supervision, lifting agentic and code performance over single-teacher OPD across multiple model sizes.
Agents-A1, a 35B MoE agent, matches or exceeds selected 1T models on long-horizon agent benchmarks by scaling trajectory length and multi-domain distillation rather than parameters.
WildRoadBench is a new dual-track benchmark on professionally annotated wild UAV road-damage images showing closed-source VLMs lead but leave over half the AP_50 metric on the table while agents lag and open-source models collapse on small targets.
Missing old logits in async agentic RL entangle discrepancy and staleness terms in PPO off-policy correction; exact acquisition methods and revised PPO-EWMA restore decoupled updates with reported gains in speed and performance.
CL-bench Life shows frontier language models achieve only 13.8% average success on real-life context tasks, with the best model at 19.3%.
NoisyAgent trains LLM agents with controlled user and tool noise to improve robustness in stochastic environments while also boosting clean-benchmark performance.
MM-ToolBench introduces 100 closed-loop multimodal tasks across two domains with 27 MCP servers and 324 tools, where agents must execute, inspect artifacts, and revise before final output.
UserGPT introduces a generative LLM framework with a behavior simulation engine, semantization module, and DF-GRPO post-training that scores 0.7325 on tag prediction and 0.7528 on summary generation on HPR-Bench while compressing records by up to 97.9%.
Technical report announcing Ling-2.6 and Ring-2.6 models with hybrid linear attention, evolutionary CoT, and KPop RL for efficient agentic intelligence at scale.
Seed2.0 model series reports gains in reasoning, visual understanding, search, and reliability on intricate long-horizon tasks via an internal evaluation system.
citing papers explorer
-
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
CLI-Universe synthesizes a verified 6K dataset of terminal-agent tasks that, when used to fine-tune Qwen3-32B, reaches 33.4% on Terminal-Bench 2.0 and sets a new open-source SOTA for models at or below 32B parameters.
-
EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent
EComAgentBench is a new benchmark with 662 tasks distributing hidden intent across sources and using source-tagged rubrics, where the strongest of seven tested models reaches only 57.1% accuracy.
-
Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning
SelSkill applies dual-granularity preference learning to selective skill-or-skip decisions, improving task success by 10.9 points and execution precision by 29.1 points on ALFWorld with Qwen3-8B.
-
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
-
AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents
AgentEscapeBench is a benchmark of 270 tasks across five difficulty tiers that measures LLM agents' ability to manage long-range tool dependencies, state tracking, and intermediate result propagation, revealing sharp performance drops with increasing depth.
-
MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
MAD-OPD recasts on-policy distillation teachers as a debating collective to supply better supervision, lifting agentic and code performance over single-teacher OPD across multiple model sizes.
-
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Agents-A1, a 35B MoE agent, matches or exceeds selected 1T models on long-horizon agent benchmarks by scaling trajectory length and multi-domain distillation rather than parameters.
-
WildRoadBench: A Wild Aerial Road-Damage Grounding Benchmark for Vision-Language Models and Autonomous Agents
WildRoadBench is a new dual-track benchmark on professionally annotated wild UAV road-damage images showing closed-source VLMs lead but leave over half the AP_50 metric on the table while agents lag and open-source models collapse on small targets.
-
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
Missing old logits in async agentic RL entangle discrepancy and staleness terms in PPO off-policy correction; exact acquisition methods and revised PPO-EWMA restore decoupled updates with reported gains in speed and performance.
-
CL-bench Life: Can Language Models Learn from Real-Life Context?
CL-bench Life shows frontier language models achieve only 13.8% average success on real-life context tasks, with the best model at 19.3%.
-
Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments
NoisyAgent trains LLM agents with controlled user and tool noise to improve robustness in stochastic environments while also boosting clean-benchmark performance.
-
TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents
MM-ToolBench introduces 100 closed-loop multimodal tasks across two domains with 27 MCP servers and 324 tools, where agents must execute, inspect artifacts, and revise before final output.
-
UserGPT Technical Report
UserGPT introduces a generative LLM framework with a behavior simulation engine, semantization module, and DF-GRPO post-training that scores 0.7325 on tag prediction and 0.7528 on summary generation on HPR-Bench while compressing records by up to 97.9%.
-
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Technical report announcing Ling-2.6 and Ring-2.6 models with hybrid linear attention, evolutionary CoT, and KPop RL for efficient agentic intelligence at scale.
-
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Seed2.0 model series reports gains in reasoning, visual understanding, search, and reliability on intricate long-horizon tasks via an internal evaluation system.