agent skills
Imagine an AI assistant that can learn from its past experiences or from code written by humans, turning that knowledge into reusable recipes. These recipes, called agent skills, let the assistant perform common tasks without starting from scratch every time. They can be stored in a library, selected efficiently based on the task, and even improved over time through trial and error.
Across the papers, a clear pattern emerges: equipping agents with skills consistently boosts their performance on diverse benchmarks, from coding challenges and game playing to image generation and mobile navigation, while cutting costs and reducing reliance on slow, expensive models. Several works also automate skill creation, selection, and refinement, showing that skills can be distilled from code repositories, self-evolved from execution feedback, or even used to train models more effectively.
- Papers
- 118
- Released code
- 10
- First seen
- Mar 2026
- Latest
- Nov 2026
98 papers in the last two months, against 12 in the two before.
Start here
Three papers to read first, in the order they came out- 1AI agents complete roughly four times as many tasks with helpers
Reusable primitives with embedded LLMs, composed per task by HEELO, solve real-world tasks that frontier models fail to complete.
Nov 2026 - 2Poisoned training tasks can backdoor self-improving AI agents
Poisoned evolution tasks can trick self-improving AI agents into building backdoors into their own skills.
Nov 2026 - 3AI agent teams consume more resources without a consistent advantage
There is no universally best agent architecture; the right choice depends on the SOP and implementation quality.
Nov 2026
How fast it is moving
Often studied with
skill evolutionThe process of developing, refining, or optimizing reusable capabilities in LLM agents through learning, adaptation, or experience accumulation.26 togetherverificationChecking outputs for correctness before accepting them, often to catch errors or reward hacking.25 togetheragent memoryA repository where an agent stores past interactions and outcomes to inform future decisions.20 togetherWho is working on it
The papers
Most central to this idea first, not most recent.
- Big Techcs.AI
AI agent teams consume more resources without a consistent advantage
There is no universally best agent architecture; the right choice depends on the SOP and implementation quality.
Amazon, University of Washington · Nov 2026
- Independentcs.CR
Poisoned training tasks can backdoor self-improving AI agents
Poisoned evolution tasks can trick self-improving AI agents into building backdoors into their own skills.
Nov 2026
- Academiccs.CL
AI agents complete roughly four times as many tasks with helpers
Reusable primitives with embedded LLMs, composed per task by HEELO, solve real-world tasks that frontier models fail to complete.
University of Illinois Urbana-Champaign, Georgia Institute of Technology · Nov 2026
- Big Techcs.CL
Agent Skills teach AI systems precise subagent permissions
Procedural knowledge in Agent Skills improves subagent authorization precision beyond what task outcomes alone provide.
Samsung Research, Peking University · Nov 2026
- Research Labcs.CL
Individually approved agent skills can combine to break workflow policies
Individually safe agent skills can combine to cause policy violations, and adding a few benign skills nearly doubles the violation rate.
University of Science and Technology Beijing, ZODA · Oct 2026
- Academiccs.CR
One in seventeen AI agent skills contains a directive that bypasses human oversight
About one in seventeen agent skills contain a directive that loosens human oversight, and existing scanners catch at most 46% of such directives.
Queen's University · Oct 2026
- Academiccs.CV
Practicing reusable web skills then composing them improves compact agents
Training web agents on reusable interaction skills, then decomposing tasks into those skills, improves success on unseen websites and external benchmarks.
University of Utah, Islamic University of Technology · Oct 2026
- Academiccs.CR
Malicious skill files can make AI agents answer forbidden questions
Jailbreaks hidden in Markdown skill files propagate through agents, raising attack success from 0.5% to 45% on average and up to 68.9%.
University of Illinois Urbana-Champaign, Argonne National Laboratory · Oct 2026
- Chinese Techcs.AI
AI web agents learn long tasks by reusing skills salvaged from failures
SCOPE achieves 3.9% to 18.6% relative gains on web tasks by progressively discovering and composing local skills.
Renmin University of China, Huawei Technologies · Nov 2026
- Big Techcs.RO
Coding agents teach humanoid robots new whole-body skills without retraining
A single frozen Metatron checkpoint supports walking, recovery, object pickup, and sitting on a real humanoid through code-defined prompts.
NVIDIA, Dollhouse Robotics · Oct 2026
- Academiccs.LG
AI agents can outline organs in scans from plain-language requests
General-purpose AI agents can automate 3D image annotation from plain language requests by prompting a segmentation model, reaching mean Dice scores of 0.81 to 0.84.
German Cancer Research Center (DKFZ), National Center for Tumor Diseases (NCT) Heidelberg · Oct 2026
- Chinese Techcs.AI
Gameplay dataset maps tasks to subgoals for training AI agents
AceAction-5M is a multi-game dataset linking task, subgoal, and skill instructions to time-aligned gameplay visuals and keyboard-and-mouse actions.
Tencent, Jilin University · Nov 2026
- Chinese Techcs.CL
Contrasting group executions pinpoints which agent skill caused success or failure
GRSE compares multiple executions of the same question to assign credit to the responsible agent and skill, outperforming prior methods.
Mayo Clinic, University of Manchester · Oct 2026
- Chinese Techcs.AI
Interleaved teaching helps agents learn skills that transfer better
Interleaving expert teaching with student practice improves transferable skill learning for LLM agents.
Nanjing University, Alibaba Group · Oct 2026
- Academiccs.CR
Security skills guide coding agents to only 11% fully correct vulnerability detection
Current security skills rarely make coding agents fully identify Linux kernel vulnerabilities, while failure-driven skill refinement substantially improves detection on unseen cases.
York University · Oct 2026
- Top Universitycs.CR
Lightweight decision model catches nearly all malicious agent skills
SkillScreen detects malicious agent skills with high recall and few false positives using a compact decision model.
University of British Columbia, University of Toronto · Oct 2026
- Chinese Techcs.AI
Skill-based benchmark reveals stark agent reliability gaps hidden by lenient scoring
AI agents achieve high completion rates but fail to meet all constraints, especially procedural ones, in realistic professional tasks.
MBZUAI, City University of Hong Kong · Oct 2026
- Research Labcs.RO
Hierarchical skill-based framework achieves high precision in robotic surgery by separating semantic decisions from low-level control
SurgiCLAW confines a multimodal language model to choosing atomic surgical skills while deterministic controllers execute them, achieving 94.6% accuracy and 88.0% real-robot success.
Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences · Oct 2026
- Big Techcs.AI
TeleTune learns agent skills from unfiltered user logs without goals or replay
TeleTune learns reusable textual skills from goal-free, non-replayable, interleaved telemetry logs by keeping only library edits that improve held-out action-prediction accuracy.
UNC Chapel Hill, University of Texas at Austin · Oct 2026
- Big Techcs.AI
Mined agent skills need domain-specific evidence and format choices
Mined skill performance depends on task domain; workflows beat ontologies on one benchmark, outcome labels help on another, but no configuration wins everywhere.
Massachusetts Institute of Technology, Microsoft Corporation · Oct 2026
- Chinese Techcs.CRcode
Skill Images Can Steer Agents Into Unauthorized Actions
Image-borne attacks in multimodal agent skills induce unauthorized operations in every tested configuration, with a 43.1% success rate.
Zhejiang University, Ant Group · Sept 2026
- Chinese Tech
Agent skill for plugin migration shows reward gains but hides grading errors
Version-specific agent skills raised plugin-migration scores, but concentrated gains and grading errors made aggregate reward unreliable evidence of contract-correct advice.
Tsinghua University, Fudan University · Sept 2026
- Research Labcs.CR
Installable agent skills can inherit user authority without adequate checks
Skill-based LLM agents allow malicious skills to reach security-sensitive operations due to systematic trust failures.
Institute of Information Engineering, Chinese Academy of Sciences, Worcester Polytechnic Institute · Oct 2026
- Top University
Benign-Looking Agent Skills Can Combine Into Harmful Cross-Skill Attacks
Skill cascading attacks distribute a malicious objective across multiple skills so each passes per-skill scans but combined execution causes harm.
The Chinese University of Hong Kong, Shenzhen, University at Buffalo, SUNY · Sept 2026
- Chinese Techcs.SE
Agents learn software repair rules that transfer across repositories
XRepoSkill learns transferable software engineering skills by deriving rules from divergent successful and failed trajectories and verifying them across repositories.
Nanyang Technological University, Tsinghua University · Sept 2026
- Chinese Techcs.CR
Informed attackers can evade static and LLM-based agent skill scanners
An informed attacker defeats static and LLM skill scanners by hiding payloads in natural language and splitting instructions across files, succeeding up to 97%.
Huawei Research Zurich · Oct 2026
- Academiccs.CL
Verified workflow training gives language models reusable procedural skills
SkillGym converts human-written agent skills into executable training environments, enabling LLMs to internalize procedural competence and beat larger models on real-world benchmarks.
East China Normal University, Shanghai AI Laboratory · Sept 2026
- Big Techcs.AI
Retrieving existing agent skills improves optimization across different execution harnesses
RASO leverages an external skill corpus through initialization and update, adapting retrieved skills across harnesses, and outperforms retrieval-free baselines on four benchmarks.
Korea University, KAIST · Sept 2026
- Independentcs.AI
Reusable code skills help language agents act and learn efficiently
Code-based skills nearly triple game progression and reduce inference cost by 86% in NetHack language agents.
Sept 2026
- Top Universitycs.AI
Compiling Mobile App Navigation Makes GUI Agents Faster and More Reliable
PhoneCLI compiles mobile app navigation into deterministic commands, reducing VLM cost and improving task success.
The University of Hong Kong · Sept 2026
- Big Techcs.AI
Learning options by focusing on relevant features instead of whole states
Identifying a small relevant subset of features per subgoal yields options that generalize broadly and accelerate exploration.
Amazon, Brown University · Sept 2026
- Independentcs.AI
Compiling agent skills into state machines improves task success
HEXIS compiles agent skills into extended finite state machines, improving success by 16.2 percentage points over Skill + ReAct and reducing execution tokens by 38.4-88.9% with Qwen3.8-27B.
Sept 2026
- Top Universitycs.SE
Reusable skills improve smart-contract audits, but model choice dominates
Model capability, not agent harness, determines skill effectiveness in smart contract auditing; triggering is a bottleneck.
Lingnan University, The Hong Kong Polytechnic University · Sept 2026
- Top Universitycs.AIcode
Bandit-guided skill evolution cuts LLM agent optimization costs
COBRA-Skills uses contextual bandits to optimize LLM agent skills, achieving top performance with 55-58% less cost than SkillOpt.
The Chinese University of Hong Kong, Shenzhen, Tianjin University · Sept 2026
- Academiccs.CR
Poisoned reference answers can implant persistent backdoors in AI agents
Poisoned reference answers can create persistent, trigger-activated backdoors in text-space skill optimization without attacker access to model or optimizer.
Yonsei University, Inha University · Nov 2026
- Big Techcs.RO
Robot coding agents learn faster with smarter feedback, not more data
Agentic robot self-learning is bottlenecked by agents' ability to interpret physical interactions into effective policy updates, not by access to information.
UC Berkeley, Bosch · Nov 2026
- Big Techcs.LG
RL method helps AI agents learn high-level task strategies from sparse rewards
A strategy-guided reinforcement learning method that routes LLM agents through hierarchical skills beats flat skill retrieval.
Microsoft AI · Nov 2026
- Chinese Techcs.CV
Visual skill representations reduce exposure-driven action bias in language model agents
Language models increasingly favor an action when its procedural pattern is repeated in a skill; visual skill representation reduces that bias.
Northeastern University, Alibaba Group · Oct 2026
- Top Universitycs.AI
AI agents can rewrite their improvement routines, outperforming human-written instructions
Skill∞ recursively improves both task skills and the meta-skill used to optimize them.
National University of Singapore, City University of Hong Kong · Oct 2026
- Academiccs.AI
Coding up definite operations improves AI agent consistency
Compiling well-specified skill operations into deterministic programs reduces execution uncertainty and improves AI agent task performance.
East China Normal University, China University of Geoscience · Oct 2026
- Chinese Techcs.AI
Teaching data agents to use charts inside their reasoning loop improves analysis
Data agents that choose charts as intermediate evidence within their reasoning loop improve analytical accuracy, and experience distillation teaches them when to draw and read charts.
Tencent, Renmin University of China · Oct 2026
- Industrycs.LG
AI agents get better at software tasks by reusing their own verified work
Generating software tasks, recording how agents execute them, and retraining on verified runs produces open-source computer-use agents that lead their size class on screen, desktop and web tests.
Shanghai Qiji Zhifeng Co., Ltd. · Nov 2026
- Top Universitycs.CR
AI email agents can handle standard phishing safely yet obey tailored attacks
Adaptive persuasive phishing attacks can evade LLM email agents' detection and trigger malicious-request compliance even when agents safely handle pre-existing phishing emails.
Carnegie Mellon University · Oct 2026
- Academiccs.AI
Agents Repair Executable Skill Packages Better With Code-Structure Guidance
SkillScriptBench shows AST-guided, scope-limited editing substantially improves reliable repair of executable agent skills while coordinating scripts and documentation.
The Hong Kong University of Science and Technology, Harbin Institute of Technology, Shenzhen, China · Oct 2026
- Chinese Techcs.CRcode
Splitting malicious actions from their rationale defeats skill-by-skill audits
Separating a poisoned agent skill's malicious operation from its fabricated justification enables effective attacks that isolated skill audits can miss.
Beihang University, Baidu Inc · Oct 2026
- Chinese Techcs.AI
LLM agents learn when to use atomic tools versus composite skills via counterfactual outcome comparisons
CIPO improves LLM agents' tool use by training them to choose between atomic tools and composite skills based on state.
Southeast University, KTH Royal Institute of Technology · Oct 2026
- Chinese Techcs.AI
Diagnosis-first framework boosts solver performance across numerical domains
ADSD links numerical diagnosis to reusable solver skill discovery, improving solver accuracy, robustness, and efficiency across four numerical domains.
University of California, Berkeley, Alibaba Group · Oct 2026
- Big Techcs.AIcode
Adaptively choosing how to revise LLM skills outperforms fixed revision strategies
StraTune adaptively selects revision operators to improve self-evolving LLM skills, outperforming fixed operators across tasks.
The University of Texas at Austin, Amazon · Sept 2026
- Chinese Techcs.AI
Statistical gates help self-editing agents avoid lasting performance regressions
SAGE uses per-item paired comparisons and one-sided paired tests to accept skill edits only when wins are statistically reliable, reducing regressions in self-evolving LLM agents.
Peking University, University of Oklahoma · Sept 2026
- Big Techcs.RO
Simulation-first framework lets coding agents learn real robot skills in 10 minutes
SimEX lets coding agents learn real robot skills by first practicing in simulation and then adapting with only 10 minutes of physical trials.
Amazon FAR, University of Texas at Austin · Oct 2026
- Chinese Techcs.AI
Contrasting multiple trajectories sharpens skill learning for LLMs
SkillCome improves skill evolution for language models by contrasting multiple successful and failed trajectories and using dual memory to derive reusable skills.
Fudan University, Ant Group · Sept 2026
- Research Labcs.CV
Visual agents improve by jointly evolving reusable skills and practice data
V-Gym co-evolves procedural skills and multimodal practice data from agent execution trajectories for continual self-improvement.
State Key Laboratory of AI Safety, Institute of Computing TechnologyChinese Academy of Sciences · Sept 2026
- Chinese Techcs.AI
Adam-inspired updates make agent skill evolution steadier and more efficient
SkillAdam uses an Adam-inspired memory and adaptive budget to stabilize and accelerate skill evolution for LLM agents.
Renmin University of China, Tencent · Sept 2026
- Academiccs.AI
Distilled repository skills improve agents conducting machine-learning research
Distilling GitHub repositories into reusable skills boosts autonomous ML research agent performance on four benchmarks.
Beijing Academy of Artificial Intelligence, University of Science and Technology of China · Sept 2026
- Industrycs.LGcode
Reusing agent trajectories cuts token use on repeated tool tasks
TRIAGE reduces token consumption in LLM agents by reusing historical execution trajectories through a three-level routing framework.
China Telecom Cloud · Sept 2026
- Top Universitycs.AI
Selecting complementary LLM skills improves success while reducing context use
Skill selection for LLM agents can be optimized as a budgeted submodular maximization problem with a bicriteria approximation guarantee.
Tsinghua University · Aug 2026
- Chinese Techcs.CL
Self-play with evolving skills boosts LLM benchmarks
Skill Self-Play pushes LLM performance ceilings by co-evolving proposer, solver, and skill controller.
Alibaba, The Chinese University of Hong Kong · July 2026
- Big Techcs.AI
Skill evolution improves agent performance in image generation workflows
Self-evolving skill libraries improve agent reliability in recurring image generation workflow construction.
University of Pennsylvania, Nvidia · July 2026
- Chinese Techcs.AI
Aligned skills and rubrics improve multimodal agent training
Representing each skill as both actor-facing guidance and an evaluator-facing rubric, then co-evolving them, improves multimodal agent planning and tool use.
The University of Hong Kong, Peking University · Sept 2026
- Chinese Techcs.AI
MetaExp trains a transferable experience-learning capability in language model agents
MetaExp trains language models to learn and reuse experience across tasks using verifiable cross-task families.
University of Macau, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences · Oct 2026
- Independentcs.AI
Self-building laboratories design and configure their own experiments from a high-level scientific goal
A self-building laboratory can design, configure, and operate its own experimental setup from a high-level goal, constructing any missing lab layout, digital twin, robot skills, and workflows.
Oct 2026
- Big Techcs.AI
Sparse rewards teach one robot policy all 20 NIST assemblies
A single reinforcement learning policy can learn all 20 NIST Assembly Task Board 1 tasks from sparse binary rewards, reaching 98.2% training success without demonstrations or shaping.
NVIDIA, University of Washington · Oct 2026
- Chinese Techcs.AI
SkillHorizon benchmark reveals that language agents struggle to complete long business workflows as task scope grows
Long-horizon agent tasks built from composed skills cause completion rates to drop from 90.4% to 46.8% as workload grows.
Hong Kong University of Science and Technology, Alibaba Group · Oct 2026
- Chinese Techcs.CL
Compiling agent trajectories into targeted long-context tasks boosts model capabilities
TrajLong compiles agent trajectories into long-context training tasks targeting evidence grounding, cross-evidence aggregation, and temporal state maintenance, improving LLM agent performance.
Hong Kong University of Science and Technology (Guangzhou), Tencent · Oct 2026
- Top Universitycs.LG
Empowerment Leads Agents to Central States, but Not Always Adaptability
Empowered states are central in information geometry, enabling task adaptation only in tabular settings.
Princeton University, UC Berkeley · Oct 2026
- Academic
Scoping Agent Memory Prevents Unrelated Tasks From Disrupting Each Other
Family-scoped retrieval prevents cross-family interference and supports repeated adaptation in persistent agent memory.
Independent, Northwestern University · Sept 2026
- Independentcs.AI
Skill-guided environment synthesis improves post-training for tool-using agents
Capability-guided synthesis turns reusable skills into executable agent-training environments, and 1.5K selected trajectories from them improve performance across multiple agent benchmarks.
Sept 2026
- Chinese Techcs.AI
Language model and skill set co-evolve through response feedback
SkillDuet coordinates model parameter updates and skill retention using response feedback, achieving 98.57% on ALFWorld and 92.97% on WebShop.
Alibaba · Nov 2026
- Top Universitycs.RO
Robot self-improvement stalls when perception, skill chains and tests mislead
An agentic robot self-improvement system failed because perception modules can't resolve relational concepts, skill chains bias learning, and evaluation harnesses misdirect optimization.
National University of Singapore · Sept 2026
- Independentcs.AI
Closed-loop development improves mobile agents across planning and tool use
Qwen-Planner-Agent uses AI agents to build and improve a mobile planner agent, outperforming prior systems on MobilePA-Bench.
Sept 2026
- Chinese Techcs.AI
Coding agents struggle with infrastructure changes that existing tests miss
InfraDev shows top coding agents succeed on only 38.9% of realistic AI infrastructure tasks.
University of Edinburgh, Tencent Hunyuan · Oct 2026
- Big Techcs.AI
Coding agents improve scientific models mostly through engineering, not insight
Frontier agents improve scientific ML benchmarks via ML engineering tricks, not research insight; plug-in skills double gains.
Anthropic Fellows Program, Anthropic · Oct 2026
- Big Techcs.MA
AI agents improve on specialized tasks with 17–38% fewer training runs
EMMA treats multi-agent configurations as episodic memory with explicit, guarded updates, outperforming baselines by up to 32.5%.
Amazon, University of California San Diego · Oct 2026
- Chinese Techcs.AI
Streaming AI assistants struggle to act on time and sustain guidance
Current Omni-LLMs fail to reliably deliver timely tool calls, query-free reminders, and complete guidance sequences on continuous audiovisual streams.
The Hong Kong Polytechnic University, Alibaba Token Hub, Alibaba Group · Oct 2026
- Industrycs.RO
Benchmark reveals when robotic agents truly learn and when they just retry
Self-improving robot agents do not necessarily learn from experience; apparent gains can come from retries or luck, and learned skills do not always transfer.
Luma AI · Oct 2026
- Top Universitycs.SE
Benchmark shows coding agents struggle to synthesize static-analysis checkers
Current coding agents reliably synthesize static-analysis checkers on fewer than half of CheckerBench tasks, with the best configuration achieving 45.33% Pass@1.
East China Normal University, Humanlaya Data · Oct 2026
- Big Techcs.HC
AI agents can repeat tasks consistently when successful runs become code
FlashScript compiles successful agent runs into neuro-symbolic programs with identical tool calls, lower token cost, and reuse on unseen instances.
University of Southern California, Microsoft · Oct 2026
- Top Universitycs.RO
Agent harness lets a pretrained multimodal LLM navigate any task without fine-tuning
A pretrained multimodal LLM delegates decision-making to navigation tools to handle any navigation task in any scene.
Zhejiang University, Shenzhen University · Oct 2026
- Big Techcs.CL
Jointly evolving algorithmic plans and code yields fast hybrid optimizers
HeurEvo jointly evolves algorithmic plans, code, and reusable components to design hybrid solver-augmented heuristics that perform well under tight runtime budgets.
Purdue University, Microsoft Research · Oct 2026
- Top Universitycs.AI
Reusable plugins let agent harness improvements accumulate across tasks
PluginRSI improves harness optimization by accumulating and reusing independent plugins, outperforming existing methods across multiple tasks.
University of Science and Technology of China, Meituan · Sept 2026
- Big Techcs.LG
Competitive self-play discovers compact motor skills humans can directly control
Competitive self-play yields a small set of motor skills that humans can directly compose to solve new tasks without retraining.
Georgia Institute of Technology, Simon Fraser University · Oct 2026
- Independentcs.LG
AI agents finish fewer than a quarter of five-stage professional tasks
On CLE, feedback and revision improve LLM agent completion by a median of 5.3 points, with the best system clearing only 47.7% of levels.
Oct 2026
- Independentcs.CL
Small AI agents can handle computer tasks with clicks and code
Mage-VL-Cowork, a 4B hybrid computer-use agent, achieves 66.0% on OSWorld-Verified via evolved harness and five-stage training.
Nov 2026
- Chinese Techcs.AI
Artifact-grounded RL trains a general frontend development agent
WebCoder uses artifact-grounded reinforcement learning to outperform proprietary models on composed frontend development tasks.
Tsinghua University, Zhipu AI · Oct 2026
- Chinese Techcs.AI
Task synthesis via artifact transitions yields long-horizon agentic trajectories.
Modeling agentic tasks as artifact transitions between input and output artifacts yields long-horizon trajectories that improve agent performance on terminal benchmarks.
City University of Hong Kong, WeChat AI, Tencent · Oct 2026
- Research Labcs.AI
Execution traces enable precise localized repair of agent memory architectures
Localized code repair using raw traces and memory state improves agent memory architectures more than coarse feedback.
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · Oct 2026
- Big Techcs.CR
Encrypted commands in AI agent skills can be decoded and executed as attacks.
Encoded instructions in third-party AI agent skills can be decoded and executed as attacks, achieving success rates up to 47.5%.
IBM Research, National Yang Ming Chiao Tung University · Oct 2026
- Big Techcs.RO
Robots improve reusable manipulation skills through guided simulation practice
RPG improves robot task success from 28.6% to 95% through autonomous practice without updating model weights.
UC Berkeley, MIT · Oct 2026
- Chinese Techcs.AI
Regularization limits agent skill growth without sacrificing downstream performance
SkillEvoReg uses dropout, complexity regularization, and counterexample validation to prevent overfitting in agent skill evolution.
Huawei Noah’s Ark Lab · Sept 2026
- Top Universitycs.AI
Shopping agents falter when user needs change across a conversation
Conversational shopping agents struggle with state tracking, constraint updates, and grounded convergence; an executable framework with explicit state management and runtime guards outperforms baselines.
JD.com, Sichuan University · Oct 2026
- Big Techcs.SE
Adaptive routing helps one language model handle mixed request types
Adaptive-GEPA learns a router and specialist programs to handle heterogeneous requests, outperforming single-program optimization.
University of Texas at Austin, University of California, Los Angeles · Oct 2026
- Chinese Techcs.AI
Branching search improves how language agents evolve reusable skill libraries
SkillVine uses branching exploration to evolve LLM agent skill libraries, outperforming linear evolution on nine of ten benchmark-model combinations.
The Chinese University of Hong Kong, Noah’s Ark Lab, Huawei Technologies · Sept 2026
- Academiccs.AI
Subtask routing halves agent inference cost while improving performance
RSI-router achieves cheaper, better agent performance by routing subtasks to different LLMs and evolving skills.
Shanghai Artificial Intelligence Laboratory · Sept 2026
- Big Techcs.PL
Agentic copilot accelerates ML accelerator co-design by grounding insights in fresh simulation data
Coco automates simulation experiments and data analysis to accelerate hardware-software co-design for ML accelerators.
Google, Google DeepMind · Oct 2026
- Top Universitycs.AI
Attribution-guided skill graphs improve targeted repairs for frozen language models
GraphSkillAA uses attribution-guided updates and two-level validation to optimize skill graphs, outperforming existing methods.
National Key Laboratory for Novel Software Technology, Nanjing University · Sept 2026
- Academiccs.AIcode
Memory lets traffic-simulation agents build reusable skills without retraining
SimSkill, a self-evolving LLM agent with episodic, procedural, and semantic memory, improves verified success on SUMO benchmarks by up to 25 percentage points.
Jilin University · Sept 2026
- Big Techcs.AI
Persistent Wikis Help AI Agents Build Better Transferable Skills
WikiSkill uses a persistent knowledge base to compile agent experience into reusable skills, outperforming existing methods.
Google Research, Virginia Tech · Aug 2026
- Independentcs.AI
DSA orchestrates evidence-aware stock research across six regional markets
DSA is an evidence-aware orchestration framework for multi-market stock research with LLM agents.
Aug 2026
- Top Universitycs.AI
Treating memory management as a trainable cognitive skill boosts LLM performance 2x–4x in long-horizon tasks
Memory management is an independently learnable skill whose automated optimization yields 2x-4x improvement on long-horizon tasks.
Stanford University · July 2026
- Chinese Techcs.CV
Unified visual-generation agentic model outperforms larger closed-source models
A single end-to-end learnable agentic model combines understanding, thinking, planning, and creation for visual tasks, outperforming larger closed-source models on a new benchmark.
Tencent Hunyuan, Hong Kong University of Science and Technology · Mar 2026
- Independentcs.AI
TROVE edits agent workflows only when runtime evidence demands it
TROVE revises only the invalidated suffix of a provisional agent route at runtime, improving quality and efficiency across code, QA, and math benchmarks.
Sept 2026
- Big Techcs.AI
Agentic verification improves outputs on long-horizon workspace tasks
VeriHarness uses the generator's own model as an agentic verifier to improve selection and revision of long-horizon task artifacts.
Google Cloud AI Research, University of Cambridge · Oct 2026
- Industrycs.AI
Programmatic code specifies agent behavior, improving robustness and efficiency
ABCAgent specifies FM agent behavior as editable Python code for robust and efficient task execution.
Uniphore · Oct 2026
- Research Labcs.CR
Privacy guidance combining instructions and metadata labels halves agent confidential access
Combining system and skill-level privacy guidance roughly halves LLM agents' use of confidential sources.
Inria, Université Paris-Saclay · Sept 2026
- Big Techcs.AIcode
Research-guided software evolution improves fixed-model agents on two benchmarks
ScholarEvolve automatically uses state-of-the-art research and topic modeling to guide agent harness evolution, improving task completion on AppWorld and Tau2-Bench.
University of California, Santa Barbara, Microsoft · Oct 2026
- Chinese Techcs.AI
Checkpoint testing reveals hidden weaknesses in self-evolving agent memories
Process-level evaluation is necessary because endpoint performance hides capability degradation in self-evolving agents.
Zhejiang University, Alibaba Group · Sept 2026
- Big Techcs.LG
Verified memories help chip-design agents transfer lessons across tasks
ChipMEM stores agent skills only after verification tools confirm they pass, improving performance on RTL designs.
University of Illinois Urbana-Champaign, NVIDIA · Sept 2026
- Top University
Self-improving agent improves automated optical lens design across diverse tasks
LensDesigner autonomously designs optical lenses by retrieving seeds from a library and self-evolving through progressively harder tasks.
INSAIT, Sofia University “St. Kliment Ohridski”, Zhejiang University · Sept 2026
- Chinese Techcs.CLcode
Self-retiring distillation improves reinforcement learning for multi-turn agents
RetireOPD adaptively removes teacher supervision during agentic RL when it no longer benefits the student.
Zhejiang University, Alibaba Group · Sept 2026
- Top Universitycs.LGcode
Graph-structured skills improve LLM agents through evolutionary optimization
Graph-structured skills improve LLM agent performance more than unstructured skill optimization.
City University of Hong Kong, National University of Singapore · Sept 2026
- Chinese Techcs.AI
Process-level tests expose distinct mathematical agent capabilities in LLMs
Process-level benchmarks reveal that LLMs with equal end-to-end accuracy can have very different agentic mathematical capability profiles.
Sun Yat-sen University, Tencent Youtu Lab · Aug 2026
- Big Techcs.AI
Post-training can replace prompt-time schema injection for enterprise coding agents
CRAFT uses two-stage post-training to embed schema knowledge into coding agents, improving analytics performance while reducing prompt token costs by 9x.
Amazon Advertising Foundations, Amazon Web Services Agentic AI · June 2026
- Big Techcs.CV
Agent framework auto-tunes video diffusion for 2x speedup
Sol Video Inference Engine uses an agent framework to automatically accelerate video diffusion models by over 2x without quality loss.
NVIDIA Research · June 2026
- Top Universitycs.AI
Benchmark tests AI's ability to infer mechanisms from data
AI agents struggle to generate mechanistic hypotheses from empirical data, leaving a large performance gap.
Computer Network Information Center, Chinese Academy of Sciences, National University of Singapore · Oct 2026
- Top Universitycs.AI
Evolved agent harnesses lift enterprise performance without retraining models
StarHarness evolves environment-specific agent harnesses, improving benchmark performance by 20-35 percentage points.
ServiceNow, Mila · Aug 2026
- AI Startupcs.CV
Multi-agent orchestration generates 3D scenes from single images
SceneConductor generates coherent 3D scenes from single images via three-stage multi-agent orchestration and geometry-aware layout prediction.
Nanyang Technological University, University of Oxford · June 2026
- Big Techcs.AI
Self-supervised method improves agent harnesses using past trajectories
Retrospective Harness Optimization improves AI agent harness using past trajectories and self-preference, boosting SWE-Bench Pro pass rate from 59% to 78% without external labels.
City University of Hong Kong, Microsoft Research Asia · June 2026
- Top Universitycs.AIcode
Re-evaluation shows harness evolution for agents may not outperform simple test-time scaling
Automatic harness evolution for LLM agents does not consistently beat simple test-time scaling and generalizes poorly to held-out tasks.
Allen Institute for AI, University of Washington · July 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.