Claims Browser

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"

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"

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."

Orientation and pedestrian-aware movement remain unreliable for current MLLM agents

"while orientation and pedestrian-aware movement remain unreliable"

Recent prompt optimizer developments favor unnecessarily complex approaches

"recent developments increasingly favor unnecessarily complex prompt optimizers"

Existing propose-and-verify methods for agent harness adaptation waste rollouts on unrelated behaviors and allow aggregate scores to obscure specific regressions

"Existing propose-and-verify methods typically score every candidate on a fixed task set, wasting rollouts on unrelated behaviors and allowing aggregate scores to obscure specific regressions."

Current LLM-based EDA systems fall into a syntax trap where models produce plausible code rather than physically correct hardware

"this reveals a syntax trap in which models are trained to produce plausible code rather than physically correct hardware, compounded by fragmented tools and loss of design context that obscure how decisions affect later stages."

Recent LLM-driven personal-health agents mainly handle short-term, retrieval-based lookups and do not evaluate whether agents can reason over long-term signals

"Recent LLM-driven personal-health agents enable natural language queries over wearable signals, but mainly handle short-term, retrieval-based lookups (e.g., highest step count over a week). They do not evaluate whether agents can reason over long-term signals to predict wellbeing scores paired with evidence-grounded rationales."

Existing work in agent domains uses domain-centered organization and heterogeneous evaluation that obscure common generation mechanisms and conflate candidate construction with verification and selection

"Existing work spans many agent domains, but domain-centered organization and heterogeneous evaluation often obscure common generation mechanisms and conflate candidate construction with verification and selection."

Agents are speaking more gobbledygook these days

"agents are speaking more gobbledy goop these days"

Large language models lack an explicit mechanism for maintaining compact and evolving conceptual representations

"Large language models process large amounts of information but usually lack an explicit mechanism for maintaining compact and evolving conceptual representations."

Current frontier agents are much stronger when source is available than when they must reason over binaries

"a companion post argues current frontier agents are much stronger when source is available than when they must reason over binaries"

Current agent evaluations are limited to narrow, verifiable tasks and cannot assess open-ended AI research capabilities

Existing agentic visual reasoning systems fail to optimize for Mode Adaptiveness and Tool Effect, leading to inefficient tool use

Vision-language models as judges of computer-using agent trajectories have not been systematically evaluated for reliability

Existing multi-agent systems typically treat communication topology as a fixed design choice or an offline optimization target, which is a limitation.

Multimodal agent evaluation that reduces to final-answer accuracy cannot distinguish whether correct answers came from grounded evidence, language priors, or accidental error cancellation

Computer-use agents often fail on transient GUI events because expensive autoregressive decoding is on the decision-time critical path

Existing post-training quantization methods are poorly suited to World Action Models because they rely on open-loop objectives, homogeneous model assumptions, and calibration distributions that do not reflect deployment