ISE creates 23,132 execution-grounded multi-turn OS agent trajectories via intent simulation and live execution, improving agent performance on ClawEval from 19.3 to 37.7 pass@1 with Qwen3-8B.
hub Mixed citations
arXiv preprint arXiv:2407.03502 , year=
Mixed citation behavior. Most common role is background (67%).
14
Pith papers citing it
Background
67% of classified citations
hub tools
citation-role summary
background 4
method 1
other 1
citation-polarity summary
representative citing papers
WhiFlash introduces token-level cross-paradigm routing between autoregressive and diffusion drafting models, with cache optimizations, to raise acceptance lengths and deliver up to 69.6% throughput gains over EAGLE-3.
WRIT is a synthesis pipeline that generates write-read intensive trajectories along axes of write-decision count and per-decision evidence burden, enabling a 4B model to outperform GPT-5.1 on τ²-bench with reduced inference tokens.
SkillGen synthesizes auditable skills from agent trajectories via contrastive induction on successes and failures, then verifies net performance impact by comparing outcomes with and without the skill on identical tasks.
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
TREX automates the LLM training lifecycle via collaborative agents and tree-based exploration, delivering consistent performance gains across 10 real-world fine-tuning tasks in FT-Bench.
DataClaw0 introduces an agentic data-tailoring paradigm, a 9B model trained on a synthetically generated dataset, and a new benchmark, claiming improved downstream adaptation in video generation, VQA, and GUI navigation under limited data.
Controlled experiments on synthetic post-training data show provenance-grounded gating and adaptive recovery improve yield and recall over baselines, with generator scale as the primary driver of downstream fine-tuning quality.
Proposes image-bank harness and ODE closed-loop data generation to boost multimodal deep search agents, reporting average score gains from 24.9% to 39.0% on 8 benchmarks for 8B model and 30.6% to 41.5% for 30B.
Kimi K2 is a 1-trillion-parameter MoE model that leads open-source non-thinking models on agentic benchmarks including 65.8 on SWE-Bench Verified and 66.1 on Tau2-Bench.
Claw-R1 provides a Gateway Server and Data Pool to manage step-level agent interaction traces as structured data assets for agentic RL training.
A 14B reasoning model trained via supervised fine-tuning on selected prompts and o3-mini traces, plus outcome RL, outperforms larger open models like DeepSeek-R1-Distill-Llama-70B on math, coding, planning and related benchmarks.
A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.
The survey organizes LLM-based multi-agent collaboration mechanisms into a framework with dimensions of actors, types, structures, strategies, and coordination protocols, reviews applications across domains, and identifies challenges for future research.
citing papers explorer
-
Kimi K2: Open Agentic Intelligence
Kimi K2 is a 1-trillion-parameter MoE model that leads open-source non-thinking models on agentic benchmarks including 65.8 on SWE-Bench Verified and 66.1 on Tau2-Bench.