Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
super hub
Kimi K2.5: Visual Agentic Intelligence
100 Pith papers cite this work. Polarity classification is still indexing.
100
Pith papers citing it
abstract
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evaluations show that Kimi K2.5 achieves state-of-the-art results across various domains including coding, vision, reasoning, and agentic tasks. Agent Swarm also reduces latency by up to $4.5\times$ over single-agent baselines. We release the post-trained Kimi K2.5 model checkpoint to facilitate future research and real-world applications of agentic intelligence.
hub tools
citation-role summary
background 2
citation-polarity summary
claims ledger
- abstract We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evalu
authors
co-cited works
years
2026 100roles
background 2polarities
background 2representative citing papers
Soohak is a new 439-problem mathematician-authored benchmark showing frontier LLMs reach only 30% on research math and fail to exceed 50% on refusing ill-posed questions.
SignSGD provably beats SGD by a factor of d under sparse noise via matched ℓ1-norm upper and lower bounds, with an equivalent result for Muon on matrices, and this predicts faster GPT-2 pretraining.
WildTableBench is the first benchmark for multimodal models on naturally occurring table images, with only one of 21 tested models exceeding 50% accuracy and most ranging from 4.1% to 49.9%.
AutoMat benchmark shows current LLM coding agents achieve at most 54.1% success when reproducing computational materials science claims from papers.
Ctx2Skill lets language models autonomously evolve context-specific skills via multi-agent self-play, improving performance on context learning tasks without human supervision.
AutoResearchBench is a new benchmark showing top AI agents achieve under 10% success on complex scientific literature discovery tasks that demand deep comprehension and open-ended search.
HWE-Bench is the first repository-level benchmark for LLM agents on real hardware bug repair, where the best agent fixes 70.7% of 417 tasks but drops below 65% on complex SoC projects.
VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
Large language models display the identifiable victim effect at roughly twice the human baseline, strongly amplified by instruction tuning and chain-of-thought prompting but inverted by reasoning-specialized models.
OccuBench is a new benchmark for AI agents on real-world occupational tasks via LLM-driven simulators, showing no model dominates all industries, implicit faults are hardest, and larger models with more reasoning perform better.
FashionMV introduces product-level multi-view CIR, a 127K-product dataset built via automated LMM pipeline, and a 0.8B ProCIR model that beats larger baselines on three fashion benchmarks.
PinpointQA is the first benchmark dataset for small object-centric spatial understanding in indoor videos, with four tasks showing MLLM capability gaps that improve via supervised fine-tuning.
ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
Chronicles-OCR is the first benchmark with 2,800 images across the complete evolutionary trajectory of Chinese characters, defining four tasks to evaluate VLLMs' cross-temporal visual perception.
AssayBench is a new gene-ranking benchmark for phenotypic CRISPR screens that shows zero-shot generalist LLMs outperform both biology-specific LLMs and trainable baselines on adjusted nDCG.
StereoTales shows that all tested LLMs emit harmful stereotypes in open-ended stories, with associations adapting to prompt language and targeting locally salient groups rather than transferring uniformly across languages.
LLM proofs for hard math problems show large differences in quality metrics like conciseness and cognitive simplicity that correctness-only tests miss, along with trade-offs between quality and correctness.
MLLMs scoring 70-83% on Cartesian visual tasks drop to 31-39% on logically equivalent polar versions, exposing reliance on grid discretization shortcuts instead of topology-invariant reasoning.
OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.
VibeProteinBench is a new benchmark evaluating LLMs on open-ended language-interfaced protein design across recognition, engineering, and generation, with no model showing strong performance in all areas.
LLM agents exhibit persistent attack-selection biases as fixed traits independent of success rates, with a bias momentum effect that resists steering and yields no performance gain.
RL training compute for logical reasoning follows a power law in proof depth whose exponent rises with logic expressiveness, and more expressive training yields larger gains on downstream benchmarks.
TEBench is a new project-level benchmark for test evolution showing coding agents achieve only 45-49% F1 on identifying tests needing changes, with stale tests hardest due to reliance on execution failures.
citing papers explorer
-
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
-
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
Soohak is a new 439-problem mathematician-authored benchmark showing frontier LLMs reach only 30% on research math and fail to exceed 50% on refusing ill-posed questions.
-
When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
SignSGD provably beats SGD by a factor of d under sparse noise via matched ℓ1-norm upper and lower bounds, with an equivalent result for Muon on matrices, and this predicts faster GPT-2 pretraining.
-
WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild
WildTableBench is the first benchmark for multimodal models on naturally occurring table images, with only one of 21 tested models exceeding 50% accuracy and most ranging from 4.1% to 49.9%.
-
Can Coding Agents Reproduce Findings in Computational Materials Science?
AutoMat benchmark shows current LLM coding agents achieve at most 54.1% success when reproducing computational materials science claims from papers.
-
From Context to Skills: Can Language Models Learn from Context Skillfully?
Ctx2Skill lets language models autonomously evolve context-specific skills via multi-agent self-play, improving performance on context learning tasks without human supervision.
-
AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
AutoResearchBench is a new benchmark showing top AI agents achieve under 10% success on complex scientific literature discovery tasks that demand deep comprehension and open-ended search.
-
HWE-Bench: Benchmarking LLM Agents on Real-World Hardware Bug Repair Tasks
HWE-Bench is the first repository-level benchmark for LLM agents on real hardware bug repair, where the best agent fixes 70.7% of 417 tasks but drops below 65% on complex SoC projects.
-
VoxSafeBench: Not Just What Is Said, but Who, How, and Where
VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
-
Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models
Large language models display the identifiable victim effect at roughly twice the human baseline, strongly amplified by instruction tuning and chain-of-thought prompting but inverted by reasoning-specialized models.
-
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation
OccuBench is a new benchmark for AI agents on real-world occupational tasks via LLM-driven simulators, showing no model dominates all industries, implicit faults are hardest, and larger models with more reasoning perform better.
-
FashionMV: Product-Level Composed Image Retrieval with Multi-View Fashion Data
FashionMV introduces product-level multi-view CIR, a 127K-product dataset built via automated LMM pipeline, and a 0.8B ProCIR model that beats larger baselines on three fashion benchmarks.
-
PinpointQA: A Dataset and Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos
PinpointQA is the first benchmark dataset for small object-centric spatial understanding in indoor videos, with four tasks showing MLLM capability gaps that improve via supervised fine-tuning.
-
Learning Agentic Policy from Action Guidance
ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
-
Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters
Chronicles-OCR is the first benchmark with 2,800 images across the complete evolutionary trajectory of Chinese characters, defining four tasks to evaluate VLLMs' cross-temporal visual perception.
-
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
AssayBench is a new gene-ranking benchmark for phenotypic CRISPR screens that shows zero-shot generalist LLMs outperform both biology-specific LLMs and trainable baselines on adjusted nDCG.
-
StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
StereoTales shows that all tested LLMs emit harmful stereotypes in open-ended stories, with associations adapting to prompt language and targeting locally salient groups rather than transferring uniformly across languages.
-
Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
LLM proofs for hard math problems show large differences in quality metrics like conciseness and cognitive simplicity that correctness-only tests miss, along with trade-offs between quality and correctness.
-
The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space
MLLMs scoring 70-83% on Cartesian visual tasks drop to 31-39% on logically equivalent polar versions, exposing reliance on grid discretization shortcuts instead of topology-invariant reasoning.
-
Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.
-
VibeProteinBench: An Evaluation Benchmark for Language-interfaced Vibe Protein Design
VibeProteinBench is a new benchmark evaluating LLMs on open-ended language-interfaced protein design across recognition, engineering, and generation, with no model showing strong performance in all areas.
-
CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
LLM agents exhibit persistent attack-selection biases as fixed traits independent of success rates, with a bias momentum effect that resists steering and yields no performance gain.
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
RL training compute for logical reasoning follows a power law in proof depth whose exponent rises with logic expressiveness, and more expressive training yields larger gains on downstream benchmarks.
-
Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution
TEBench is a new project-level benchmark for test evolution showing coding agents achieve only 45-49% F1 on identifying tests needing changes, with stale tests hardest due to reliance on execution failures.
-
AffectSeek: Agentic Affective Understanding in Long Videos under Vague User Queries
AffectSeek is an agentic framework that localizes affective moments, classifies emotions, and generates rationales in long videos under vague user queries, backed by the new VQAU-Bench benchmark.
-
AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification
AstroAlertBench evaluates multimodal LLMs on astronomical classification accuracy, reasoning, and honesty using real ZTF alerts, revealing that high accuracy often diverges from self-assessed reasoning quality.
-
MolViBench: Evaluating LLMs on Molecular Vibe Coding
MolViBench is the first benchmark designed to evaluate LLMs on generating executable programs for molecular tasks in drug discovery.
-
Training Computer Use Agents to Assess the Usability of Graphical User Interfaces
uxCUA is a trained computer use agent that assesses GUI usability more accurately than larger models by learning to prioritize and execute important user interactions on labeled interface datasets.
-
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
AHE automates coding-agent harness evolution via component, experience, and decision observability, raising Terminal-Bench 2 pass@1 from 69.7% to 77.0% with transfer gains across models and benchmarks.
-
Benchmarking and Improving GUI Agents in High-Dynamic Environments
DynamicUI improves GUI agent performance in high-dynamic environments by processing interaction videos with frame clustering, action-conditioned refinement, and reflection, outperforming prior approaches on the new DynamicGUIBench spanning ten applications.
-
SketchVLM: Vision language models can annotate images to explain thoughts and guide users
SketchVLM lets VLMs generate non-destructive SVG annotations on input images to visually explain answers, raising visual reasoning accuracy by up to 28.5 points and annotation quality by 1.48x over baselines.
-
MathDuels: Evaluating LLMs as Problem Posers and Solvers
Self-play between LLMs for problem authoring and solving, scored via Rasch modeling, shows that authoring and solving skills are partially decoupled and that the benchmark difficulty evolves with new models.
-
Synthesizing Multi-Agent Harnesses for Vulnerability Discovery
AgentFlow uses a typed graph DSL covering roles, prompts, tools, topology and protocol plus a runtime-signal feedback loop to optimize multi-agent harnesses, reaching 84.3% on TerminalBench-2 and discovering ten new zero-days in Chrome including two critical sandbox escapes.
-
Single-Language Evidence Is Insufficient for Automated Logging: A Multilingual Benchmark and Empirical Study with LLMs
MultiLogBench shows that LLM performance on automated logging varies substantially across programming languages, demonstrating that single-language evidence is insufficient for general claims about model behavior or tool design.
-
S-GRPO: Unified Post-Training for Large Vision-Language Models
S-GRPO unifies SFT and RL for LVLMs via conditional ground-truth injection that supplies a maximal-reward anchor when group exploration fails completely.
-
RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management
RiskWebWorld is the first realistic interactive benchmark for GUI agents in e-commerce risk management, revealing a large gap between generalist and specialized models plus RL gains.
-
Many-Tier Instruction Hierarchy in LLM Agents
ManyIH and ManyIH-Bench address instruction conflicts in LLM agents with up to 12 privilege levels across 853 tasks, revealing frontier models achieve only ~40% accuracy.
-
ClawBench: Can AI Agents Complete Everyday Online Tasks?
ClawBench is a benchmark of 153 live-web tasks where AI agents achieve low success rates, e.g. 33.3% for Claude Sonnet 4.6.
-
Learning to Interrupt in Language-based Multi-agent Communication
HANDRAISER learns optimal interruption points in multi-agent LLM communication using estimated future reward and cost, achieving 32.2% lower communication cost with comparable or better task results across games, scheduling, and debate.
-
DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions
DetailVerifyBench supplies 1,000 images and densely annotated long captions to evaluate precise hallucination localization in multimodal large language models.
-
EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents
EpiBench is a new episodic multi-turn multimodal benchmark where even leading AI agents score only 29.23% on hard tasks requiring cross-paper evidence integration from figures and tables.
-
MMORF: A Multi-agent Framework for Designing Multi-objective Retrosynthesis Planning Systems
MMORF provides a modular multi-agent framework for multi-objective retrosynthesis planning, with MASIL and RFAS systems showing strong safety, cost, and success metrics on a new 218-task benchmark.
-
Self-Distilled RLVR
RLSD mixes self-distillation for token-level policy difference magnitudes with RLVR for reliable update directions from response correctness to reach higher convergence and better training stability.
-
AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits
AgentSZZ is an LLM-agent framework that identifies bug-inducing commits with up to 27.2% higher F1 scores than prior methods by enabling adaptive exploration and causal tracing, especially for cross-file and ghost commits.
-
HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models
HumorRank ranks nine LLMs on textual humor using GTVH-grounded pairwise tournaments and Adaptive Swiss aggregation on the SemEval-2026 MWAHAHA dataset, finding that comedic mechanism mastery matters more than scale.
-
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
MinT enables efficient management of million-scale LoRA-adapted LLM policies over shared 1T-parameter base models by moving only small adapters through training and serving pipelines.
-
MMSkills: Towards Multimodal Skills for General Visual Agents
MMSkills turns public interaction trajectories into compact multimodal skill packages that visual agents can consult at runtime to improve decision-making on benchmarks.
-
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
-
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
Missing old logits in async agentic RL entangle discrepancy and staleness terms in PPO off-policy correction; exact acquisition methods and revised PPO-EWMA restore decoupled updates with reported gains in speed and performance.
-
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
LLaVA-UHD v4 reduces visual-encoding FLOPs by 55.8% for high-resolution images in MLLMs via slice-based encoding plus intra-ViT early compression while matching or exceeding baseline performance on document, OCR, and VQA benchmarks.