Agents

LLM agents and the systems around them: harnesses and orchestration, tool use and MCP, multi-agent systems, agent memory and planning

600 articles · page 7 of 13

Agents

Adaptive judges help embodied agents improve as failure patterns change

Zhou and colleagues introduce VeriFine, an agent framework designed to prevent self-improvement from stalling when an evaluator can no longer reliably recognize a policy’s emerging errors. In driving and robot-navigation experiments, the authors report continued gains by alternating policy optimization with targeted refinement of a reference-free judge, using limited human guidance when verification becomes the bottleneck.

Agents

Compiling agent trajectories into targeted long-context tasks boosts model capabilities

The authors introduce TrajLong, a framework that compiles LLM agent trajectories into long-context training tasks targeting three atomic capabilities: evidence grounding, cross-evidence aggregation, and temporal state maintenance. Mid-training Qwen3-14B and 30B models with TrajLong data followed by supervised fine-tuning yields broad gains on 6 long-context and 12 agent benchmarks, outperforming both raw and masked trajectory baselines under matched training budgets.

Agents

Workspace-grounded synthesis scales verifiable training for long-horizon work agents

Zhang and colleagues introduce WorkForge, a pipeline for creating training environments in which agents must navigate multiple files and produce professional deliverables over extended interactions. Post-training a Qwen3.5 model on solver trajectories from these environments produced large reported gains on two work-agent benchmarks, while controlled experiments found benefits from both more data and longer trajectories.

Agents

Mined agent skills need domain-specific evidence and format choices

The authors compare six combinations of mining evidence (successful traces only, successes and failures with labels, or the same mix without labels) and skill form (ordered workflow plans or declarative ontologies) while holding the mining pipeline fixed. They find that no single configuration dominates: the best choice depends on the domain and task structure, with workflows and contrastive evidence helping in some settings and ontologies in others.

Agents

TeleTune learns agent skills from unfiltered user logs without goals or replay

The authors introduce TeleTune, a method for building a library of textual skills and workflows from offline telemetry logs that have no recorded goals, cannot be replayed, and may interleave multiple tasks. Using only action-prediction errors on the logs as a learning signal, TeleTune proposes edits to the library and retains only those that improve accuracy on held-out trajectories. On WorkArena and Online-Mind2Web, TeleTune achieves average success rates of 77.1% and 80.6%, outperforming the strongest baselines by 6.7% and 7.7% respectively.

Agents

Agent control over candidate processing improves search agent performance

A team from Zhejiang University, Tencent, and Peking University introduces Programmatic Search Agent (PSA), which gives agents control over how retrieved candidates are processed and presented, not just query reformulation. Across two benchmarks with five policy backbones, PSA improves task success by 4–7.5 percentage points and reduces final-step tokens by 28–34%, confirming that evidence delivery is a critical bottleneck in search agents.

Agents

Hierarchical latent models improve long-horizon visual planning with less compute

Zhang et al. trained a hierarchy of action-conditioned Joint-Embedding Predictive Architectures, or JEPAs, which predict future representations rather than reconstructing pixels. Each level operates over a longer temporal stride and in its own latent space, allowing upper levels to represent slower, more predictable aspects of an environment. Across simulated tasks, this hierarchy improved planning success while reducing test-time search, including a rise from 18% to 73% success on Visual AntMaze.

Agents

Bilevel optimization bridges the retriever-policy credit gap in agentic RL

The authors identify an information-credit gap in agentic reinforcement learning (ARL) for LLMs: when failures arise from poor retrieval, the fixed retriever escapes blame while the LLM policy is penalized. They formulate retrieval-augmented ARL as a bilevel optimization problem, then introduce BRIDGE, a memory-efficient first-order method that updates a low-rank retriever adapter using both RL credit and a RAG likelihood term, followed by LLM policy updates. Across seven open-domain QA benchmarks, BRIDGE achieves the highest average accuracy with both 3B and 7B backbones, improving the multi-hop average over the strongest baseline by 9.6 and 3.4 exact-match (EM) points respectively.

Agents

Jointly evolving algorithmic plans and code yields fast hybrid optimizers

The authors propose HeurEvo, an automated framework that co-evolves algorithmic plans, executable code, and a shared component pool to generate hybrid optimization algorithms. Evaluated on combinatorial optimization, MIPLIB-NL, and nonlinear geometry problems under a two-minute execution budget, HeurEvo often matches or surpasses solvers running for hours or days, and on some geometry problems it improves previously reported best results.

Agents

First benchmark and method for team-based vision-and-language navigation under constraints

Xu and Liu present the first systematic formalization of multi-agent Vision-and-Language Navigation (VLN) as a coordination problem with subtask dependencies, resource constraints, and collision avoidance. They introduce the MAVLN benchmark with 11,724 episodes across 145 scenes for teams of two to four agents, and propose TRISS, a system combining an LLM-based scheduler, shared topological memory, and conflict-aware execution. Experiments show that while TRISS provides a baseline, significant room for improvement remains in scheduling, planning, and execution.

Agents

Agentic copilot accelerates ML accelerator co-design by grounding insights in fresh simulation data

The authors present Coco, an agentic platform for hardware-software co-design of ML accelerators, deployed with TPU architects. By storing every simulation sweep in a relational database and encoding recurring workflows as agentic tools, Coco reduces the manual archaeology of simulation results from hours to minutes, with early deployment showing reduction in time-to-simulation and time-to-insight.

Agents

Codetta protocol enables high-capacity, keyless, undetectable steganography for LLM agents

Qi Pang, Virginia Smith, and Wenting Zheng propose Codetta, a steganographic protocol that allows independently deployed LLM agents to communicate covertly without a pre-shared key. The protocol achieves high capacity while maintaining provable undetectability. On three agent workloads, Codetta transmits up to 94 times more bits per visible token than the prior state-of-the-art asymmetric protocol.

Agents

Evidence-driven harness edits improve frozen GUI agents across benchmarks

Yang et al. introduce an automated method for improving the runtime harness around a GUI agent without changing the underlying model. Across six backbones on OSWorld-Verified, the authors report consistent held-out improvements, including a 12.33-point gain for Qwen3-VL-32B-Instruct. A harness optimized on one benchmark also transferred to WindowsAgentArena, where it improved GPT-5 by 13.87 percentage points.

Agents

Visual memory harness helps multimodal agents solve long interactive tasks

Han et al. introduce VISTA, a model-agnostic harness designed to extend multimodal agents beyond their immediate visual context. Rather than compressing each observation once and relying on that representation throughout a task, VISTA stores past images in their original form and lets the model actively retrieve and arrange them as reasoning proceeds. With Claude Opus 5.0, this approach completed all 25 public ARC-AGI-3 games and achieved the benchmark’s maximum Relative Human Action Efficiency score.

Agents

Reusable reasoning choices make multimodal search agents substantially faster

Zhu et al. introduce Selection-based Structured Reasoning (SSR), which asks a multimodal search agent to choose among reusable natural-language reasoning templates rather than generate a new rationale token by token before every action. Across seven benchmarks with 2B and 4B parameter models, the authors report performance competitive with similarly sized search agents, alongside more than 90% lower per-turn reasoning latency and 28% to 54% lower total model inference latency per question.