Research Papers Rankings
Agent papers from the last 90 days — tool use, computer use, coding agents, multi-agent systems. Ranked by three independent signals: GitHub star velocity on the official implementation, citation count, and Hugging Face attention. Papers strong on only one signal are left out. Rebuilt every day.
LingBot-World 2.0 upgrades the game world model to an unbounded interaction horizon with consistent output quality via a causal pretraining paradigm, distills a real-time variant fast enough to drive 720p video at 60 fps, and greatly expands the action set (attacking, archery, spell-casting, shooting) plus text-driven interactive elements.
FreeToken rethinks local inference around two realities of edge AI: agent workloads keep changing shape, and every machine's resource balance differs. It co-designs model layout, expert residency, CPU-GPU execution and memory management instead of committing to a fixed offloading strategy.
Prime Agent is an open harness for long-horizon coding agents built on the Recursive Language Model idea: a persistent IPython session does test-time computation, while histories, memories, skills and subagent specs carry over between runs.
LLM-as-a-Verifier turns a language model into a verifier by computing expectations over its scoring-token logits instead of prompting for discrete judgments, yielding continuous feedback with no extra training. The authors report state-of-the-art results on benchmarks including Terminal-Bench V2 and SWE-Bench Verified, and ship a Claude Code extension that watches agents and supplies dense rewards for RL.
ABot-World-0 is an action-conditioned video world model trained on multi-source data from AAA games, simulation engines and internet videos, controlled through raw keyboard input with reference-character memory for consistent third-person rollouts. The authors report streaming 720p at up to 16 FPS on one RTX 5090 with 1.2s action-to-first-frame latency, targeting real-time long-horizon closed-loop interaction.
OSWorld 2.0 from the xlang-ai team replaces short scripted tasks with 108 long-horizon computer-use workflows built on authentic artifacts and stateful user profiles; humans take a median of about 1.6 hours per task. The headline finding is how far agents still are: the best model, Claude Opus 4.8, completes only 20.6% of tasks, often losing track of constraints or skipping verification.
Apodex 1.1 targets what the authors call working capability: it scales up the diversity and verifiability of executable file, search and code environments, while training agents to decompose long-horizon tasks, delegate parallel work and integrate asynchronous results.
This survey decomposes a self-improving agent into a foundation model and an operational scaffold of prompts, memory, tools and control logic, then defines improvement as a self-induced update operator that converts experience into accumulated capability with minimal human input. It organizes the growing literature by update target and driving signal, from prompt and memory edits to weight-level self-modification.
WeMM-Embedding is a family of universal multimodal embedding models (2B, 4B and 9B) covering text, images, video, visual documents and arbitrarily interleaved inputs, with flexible output dimensions, trained by large-scale alignment followed by refinement with curated relevance supervision.
AutoResearch connects idea generation with idea execution: candidate ideas are formed by integrating fresh research signals with accumulated domain knowledge and cross-reviewed by multiple models, then coordinated agents decompose the plans and establish them through actual experimentation.
This harness maintains an explicit task state outside the agent's execution context and updates it only with facts independently verified from the environment, using a Manage-Execute-Audit loop so mistaken self-assessments do not snowball across many steps.
AutoDesign treats multimodal conference-poster generation as a long-horizon agentic process: a meta-harness optimizer reads rollout feedback and rewrites the harness the code agent runs on. On the authors' 100-paper PosterBench it scores above Claude Design, the learned harness lifts seven different code-agent configurations, and a fully autonomous loop makes 253 tool calls in 40 minutes for under $3.
SEED converts an agent's own completed on-policy trajectories into natural-language hindsight skills and distills the behavioral shift they induce back into the policy, producing a dense token-level training signal alongside outcome-based RL. The authors report gains in sample efficiency, final performance and generalization to unseen text- and vision-based agentic tasks.
Ouroboros is a self-developing coding-agent harness whose tools, prompts, context assembly and even core implementation improve through reviewed commits that become its later runtime, with two evolution modes: recursive free evolution and experience-driven core evolution. The authors also report a 161-day live deployment across seven human communication surfaces, arguing safety guardrails must stay authoritative while the agent rewrites its own code.
Show-Harness is an open-source embodied harness that exposes discrete semantic action units for a VLM to reason over, while deterministic, embodiment-specific interpreters convert those units into low-level robot commands. The authors show the same interface lets a closed-source frontier VLM control robots zero-shot and turns a small open VLM into a planner-free policy with only a few GPU-hours of fine-tuning; its GUMI browser interface also lets humans or GUI agents collect robot demonstrations without teleoperation hardware.
Agent papers from the last 90 days — tool use, computer use, coding agents, multi-agent systems. Ranked by three independent signals: GitHub star velocity on the official implementation, citation count, and Hugging Face attention. Papers strong on only one signal are left out. Rebuilt every day.
A dash means the signal was unavailable, not zero.