Defines 3D Instruction Ambiguity Detection as a new task, releases the Ambi3D benchmark, shows state-of-the-art 3D LLMs struggle with it, and proposes the AmbiVer framework that gathers multi-view visual evidence to guide VLMs in judging ambiguity.
Robots that ask for help: Uncertainty alignment for large language model planners
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
Language models produce overcomplete reasoning traces where on average 46% of steps can be removed while preserving the answer in 86% of cases, with necessity concentrated in the top three steps.
LLM+P lets LLMs solve planning problems optimally by converting them to PDDL for classical planners and back to natural language.
A kNN lower-confidence-bound approach for act-or-defer decisions in multi-agent LLM debates respects user-declared wrong-action budgets while achieving high automation rates on benchmarks.
A small RL-trained policy for stepwise model routing between LLM sizes improves the accuracy-cost tradeoff on math benchmarks over handcrafted strategies and matches large process reward model methods.
Geometry-calibrated conformal abstention lets language models abstain from uncertain queries with finite-sample guarantees on both participation rate and conditional correctness of answers.
KGLAMP uses a dynamically updated knowledge graph to guide LLMs in creating and replanning PDDL specifications for heterogeneous multi-robot teams, reporting at least 25.3% better performance than LLM-only or classical PDDL baselines on the MAT-THOR benchmark.
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
TaskGround introduces a Ground-Infer-Execute framework for full-scene household reasoning that improves success rates on the FullHome benchmark and enables compact models to match larger ones at up to 18x lower token cost.
VizCopilot integrates topic modeling with document visualization to support user oversight of retrieved context in enterprise chatbots, enabling detection of misalignments and adaptation of prompting strategies.
citing papers explorer
-
3D Instruction Ambiguity Detection
Defines 3D Instruction Ambiguity Detection as a new task, releases the Ambi3D benchmark, shows state-of-the-art 3D LLMs struggle with it, and proposes the AmbiVer framework that gathers multi-view visual evidence to guide VLMs in judging ambiguity.
-
Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces
Language models produce overcomplete reasoning traces where on average 46% of steps can be removed while preserving the answer in 86% of cases, with necessity concentrated in the top three steps.
-
Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds
A kNN lower-confidence-bound approach for act-or-defer decisions in multi-agent LLM debates respects user-declared wrong-action budgets while achieving high automation rates on benchmarks.
-
Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
A small RL-trained policy for stepwise model routing between LLM sizes improves the accuracy-cost tradeoff on math benchmarks over handcrafted strategies and matches large process reward model methods.
-
Geometry-Calibrated Conformal Abstention for Language Models
Geometry-calibrated conformal abstention lets language models abstain from uncertain queries with finite-sample guarantees on both participation rate and conditional correctness of answers.
-
KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning
KGLAMP uses a dynamically updated knowledge graph to guide LLMs in creating and replanning PDDL specifications for heterogeneous multi-robot teams, reporting at least 25.3% better performance than LLM-only or classical PDDL baselines on the MAT-THOR benchmark.
-
Code as Agent Harness
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
-
TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
TaskGround introduces a Ground-Infer-Execute framework for full-scene household reasoning that improves success rates on the FullHome benchmark and enables compact models to match larger ones at up to 18x lower token cost.