Claims Browser

Errors accumulate without effective correction in MLLM agents during extended urban exploration

"errors accumulate without effective correction"

MLLM agents' local abilities do not compose into sustained goal-directed behavior over extended exploration

"Their central failure emerges over extended exploration, where local abilities do not compose into sustained goal-directed behavior and errors accumulate without effective correction"

Agent skills package specialized knowledge and workflows into reusable resources that enable progressive adaptation through interaction

"Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities"

Skill evolution complements model scaling as an approach to improving agent capabilities

"skill evolution complements model scaling"

Persistent knowledge accumulation in the wiki is critical for effective skill evolution

"persistent knowledge accumulation in the wiki is critical for effective skill evolution"

Evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills

"evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills"

Larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them

"larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them"

WikiSkill consistently outperforms state-of-the-art skill-evolution methods across diverse benchmarks and models

"Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods"

Process quality, result quality, and data representativeness are effective criteria for selecting high-quality agent training trajectories

"the first stage performs trajectory-level screening based on process quality, result quality, and data representativeness, selecting a high-quality and representative subset of successful trajectories."

Multi-granularity data selection that filters at trajectory and segment levels improves training efficiency and model performance for software engineering tasks

"training on the 10% trajectory subset selected by SWE-Prime outperforms training on the full resolved dataset, yielding relative performance gains of up to 12.2% and 24.2%, respectively."

Training on successful agent trajectories can introduce noisy supervision because successful trajectories may contain ineffective, redundant, or risky steps

"task success does not guarantee high-quality supervision: successful trajectories may still contain ineffective, redundant, or risky steps. Directly using such trajectories for SFT can introduce noisy supervision and encourage models to imitate undesirable problem-solving behaviors."

LLMs in code review exhibit critical weaknesses such as cross-round temporal misalignment and inadequate long-range memory

"our in-depth error analysis dissects the distinct drivers of false positives and false negatives, revealing critical weaknesses such as cross-round temporal misalignment and inadequate long-range memory"

LLMs' performance in code review varies substantially across different defect types and severity levels, with semantically complex or low-salience defects being significantly more likely to be missed

"LLMs' performance varies substantially across different defect types and severity levels, with semantically complex or low-salience defects being significantly more likely to be missed"

Mainstream LLMs exhibit limited overall performance in defect detection and defect lifecycle state tracking, with performance degrading significantly as the number of interaction rounds increases

"experiments reveal that mainstream LLMs exhibit limited overall performance in defect detection and defect lifecycle state tracking, with performance degrading significantly as the number of interaction rounds increases"

Most existing LLM approaches to automated code review oversimplify code review into a single-round, static decision task, failing to capture the multi-round interactive nature of realistic review scenarios

"Although recent work explores large language models (LLMs) for automated code review, most approaches oversimplify code review into a single-round, static decision task, which fails to capture the multi-round interactive nature and the complex problem-solving processes inherent in realistic review scenarios"

The Persona-Execution Separation pattern applies when multi-user deployment, execution audit, and expected persona churn hold jointly.

"The pattern applies when multi-user deployment, execution audit, and expected persona churn hold jointly."

Pre-separation architecture analysis revealed that the governed execution path was decoupled from the persona by omission rather than by construction, creating a risk that later wiring changes could reverse isolation, which PES prevents by making it an audited architectural rule.

"A probe of a recovered pre-separation build found the governed execution path decoupled from the persona by omission, not by construction; a later wiring change could reverse that isolation, which PES makes an audited architectural rule."

A development/pilot case in a regulated digital-employee platform demonstrated PES implementation across five decisions over one month, with mechanism checks confirming no execution-side re-validation under persona perturbation and no persona fingerprint on hard-asserted fields.

"A development/pilot case in a regulated digital-employee platform records five decisions over one month, each with a rejected alternative. A mechanism check on the shipped implementation found no execution-side re-validation under persona perturbation (five model configurations) and no persona fingerprint on hard-asserted fields."